© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2913
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming keywords

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

    The neuron fires on import statements in code (i.e. lines where modules or functions are brought in).

    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
    PointerException
    -0.81
    LayoutStyle
    -0.78
    宁
    -0.75
    tifully
    -0.75
     collation
    -0.73
     polycarbonate
    -0.72
    谔
    -0.72
     دی
    -0.72
     ו
    -0.71
    ação
    -0.71
    POSITIVE LOGITS
    Få
    1.00
    lampada
    0.98
    素晴
    0.94
     marinho
    0.94
    Bety
    0.92
    ××
    0.91
     nn
    0.91
    ristorante
    0.89
     messa
    0.87
    améli
    0.87
    Activations Density 0.009%

    No Known Activations