© 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. 22-GEMMASCOPE-RES-131K
    7. 16409
    Prev
    Next
    INDEX
    Explanations

    code keywords with punctuation

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

    The neuron activates on module, package, or decorator names in import/require statements (i.e. library identifiers).

    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
     until
    -0.93
     Divulgação
    -0.92
    orodos
    -0.90
    🦭
    -0.85
     hybride
    -0.84
     apartament
    -0.84
     botines
    -0.84
    NotImplemented
    -0.84
     basili
    -0.82
    ֮
    -0.82
    POSITIVE LOGITS
    –
    0.96
    quante
    0.95
    логии
    0.94
    always
    0.94
     śnie
    0.93
    €“
    0.90
    を設定
    0.89
     predis
    0.88
    soi
    0.87
     داشته
    0.86
    Activations Density 0.007%

    No Known Activations