© 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. 34-GEMMASCOPE-RES-131K
    7. 106808
    Prev
    Next
    INDEX
    Explanations

    import ` or `/` inside code

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

    The neuron fires on code‐style tokens—especially isolated digits, version numbers, and underscores (and the words they connect) in programming 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_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
    他要
    -0.92
     menyebutkan
    -0.88
     physically
    -0.85
     small
    -0.84
     их
    -0.81
     poniżej
    -0.79
     where
    -0.78
    ｎ
    -0.76
     funkcjon
    -0.76
     tipped
    -0.76
    POSITIVE LOGITS
    TABLES
    0.94
    HandlerContext
    0.92
    documentElement
    0.92
     deberán
    0.90
    Очень
    0.88
    ያ
    0.86
    Masa
    0.85
    俳優
    0.85
    Однако
    0.85
     miserably
    0.85
    Activations Density 0.001%

    No Known Activations