© 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. 34-GEMMASCOPE-RES-131K
    7. 58268
    Prev
    Next
    INDEX
    Explanations

    author references or citations

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

    The neuron specializes in spotting standalone numeric identifiers (e.g. reference or section numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     their
    -1.46
     there
    -1.44
     even
    -1.30
     what
    -1.30
     unrelenting
    -1.20
     oftentimes
    -1.17
     because
    -1.17
     meticulously
    -1.16
     supremely
    -1.16
     all
    -1.14
    POSITIVE LOGITS
    3
    1.19
     revamped
    1.12
     immense
    1.11
    picked
    1.06
    2
    1.05
     Dinas
    1.05
     permettant
    1.04
     enraged
    1.03
    8
    1.02
    particularly
    1.01
    Activations Density 0.011%

    No Known Activations