© 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. 10-GEMMASCOPE-RES-131K
    7. 15526
    Prev
    Next
    INDEX
    Explanations

    get context or variable

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

    This neuron activates on programming identifiers or constants containing underscore characters.

    oai_token-act-pair · o4-miniTriggered 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
     -
    -1.94
    h
    -1.88
    of
    -1.84
     who
    -1.84
    r
    -1.84
     Its
    -1.82
    Its
    -1.80
     its
    -1.80
     –
    -1.74
    es
    -1.72
    POSITIVE LOGITS
    ihnachts
    1.79
    rédients
    1.68
     tanques
    1.67
    ihnachten
    1.64
     cilindros
    1.60
     wezen
    1.54
    のでしょう
    1.50
    嗄
    1.48
     kostet
    1.47
     fábricas
    1.45
    Activations Density 0.016%

    No Known Activations