© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62485
    Prev
    Next
    INDEX
    Explanations

    programming and data schema

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

    The neuron activates on numeric tokens (i.e. any multi-digit numbers or version identifiers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Scho
    -0.75
    :_
    -0.74
    (
    -0.71
    loff
    -0.70
    )，
    -0.68
    moz
    -0.68
     layer
    -0.68
    onDelete
    -0.67
    searchTerm
    -0.67
    返す
    -0.66
    POSITIVE LOGITS
    飛行機
    0.72
    邨
    0.72
    每一次
    0.71
    過去の
    0.67
     состоит
    0.67
    喹
    0.66
    いけ
    0.65
    遡
    0.65
     кос
    0.64
     obscene
    0.63
    Activations Density 0.082%

    No Known Activations