© 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. 22-GEMMASCOPE-RES-131K
    7. 71931
    Prev
    Next
    INDEX
    Explanations

    programming code syntax

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

    The neuron fires on code tokens that perform data‐writing or serialization operations (e.g. write, Write, setItem, JSON.stringify).

    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
     but
    -1.05
    <?
    -1.02
     impe
    -0.97
    楽しめます
    -0.94
    rung
    -0.92
    But
    -0.92
     altre
    -0.92
     nhưng
    -0.91
    ?????
    -0.91
    리고
    -0.90
    POSITIVE LOGITS
     in
    1.07
     of
    0.99
     ulicy
    0.98
     aldri
    0.87
     alemán
    0.86
    Ͷ
    0.85
    selo
    0.85
     кажется
    0.84
     trucos
    0.84
     Dě
    0.84
    Activations Density 0.012%

    No Known Activations