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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104669
    Prev
    Next
    INDEX
    Explanations

    kreatel linux gnu cross-compilers

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

    The neuron is firing on standalone numeric tokens (numbers or number-like strings) in the document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    bof
    -1.02
     instead
    -0.96
     even
    -0.93
     When
    -0.92
     for
    -0.92
     Эти
    -0.92
     still
    -0.91
     Posteriormente
    -0.90
     more
    -0.89
     Unterrichts
    -0.89
    POSITIVE LOGITS
    TypedDataSet
    1.32
    DMETHOD
    1.20
     Cataloging
    1.16
     rése
    1.15
     lesquelles
    1.12
     états
    1.11
     rêver
    1.11
     médec
    1.11
    țele
    1.08
     bluza
    1.08
    Activations Density 0.004%

    No Known Activations