© 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. 10-GEMMASCOPE-RES-131K
    7. 8134
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific tokens

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

    This neuron activates on mixed-case identifier tokens (CamelCase names like isRequired, StringBuilder, UITextField).

    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
    ’
    -3.09
    ,’
    -2.17
    ’,
    -2.16
    s
    -2.09
     was
    -2.06
     ‘
    -2.02
    ;
    -1.97
    —
    -1.89
    <em>
    -1.80
    -1.78
    POSITIVE LOGITS
    嗬
    2.34
    脔
    1.96
     bricola
    1.88
    ㌧
    1.80
     desmotiv
    1.78
     kontaktu
    1.76
     StringBuilder
    1.75
     zara
    1.74
    
    1.72
     menyebabkan
    1.70
    Activations Density 0.000%

    No Known Activations