© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66652
    Prev
    Next
    INDEX
    Explanations

    code imports and property access

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

    The neuron fires on numeric literals (e.g. integers or floats) in code.

    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
     in
    -2.33
     because
    -2.30
     having
    -2.19
     has
    -2.02
     being
    -1.98
     by
    -1.98
    !!!!
    -1.98
     when
    -1.97
     at
    -1.91
    !!
    -1.88
    POSITIVE LOGITS
    鹩
    2.06
     ་
    2.05
    阏
    2.02
    歺
    1.99
    
    1.98
    鮰
    1.98
    婠
    1.95
     avancer
    1.92
     花纹
    1.91
     varier
    1.90
    Activations Density 0.010%

    No Known Activations