© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14262
    Prev
    Next
    INDEX
    Explanations

    description of [

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric tokens—both integers and decimal numbers—marking quantities, measurements, years, counts, or other numerical values in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words immediately followed by attached numeric citations or annotations in academic/technical text.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    The neuron activates for the preposition "of" when it appears in formal or technical contexts, particularly in academic papers, patents, and scientific documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -1.44
     também
    -1.30
     moreover
    -1.27
    this
    -1.24
     ricette
    -1.16
     disediakan
    -1.16
    liegenden
    -1.13
    癪
    -1.13
     myös
    -1.13
     también
    -1.13
    POSITIVE LOGITS
    )
    1.40
    ).
    1.30
     -
    1.16
    italy
    1.15
     use
    1.13
    gsmål
    1.09
    pgfmath
    1.05
    懲
    1.04
     harga
    1.02
     where
    1.02
    Activations Density 0.228%

    No Known Activations