© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119173
    Prev
    Next
    INDEX
    Explanations

    function create, void, On, Phantom Gourmet

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

    The neuron consistently lights up on tokens that are part of code method or function declarations (e.g. return‐type keywords like “void” or type names in signature lines).

    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
     istrinya
    -0.81
    struzioni
    -0.75
    ưỡng
    -0.74
    luğu
    -0.74
    midler
    -0.71
    smöglichkeiten
    -0.71
    umah
    -0.71
    ⽂
    -0.71
     MMMM
    -0.70
    antal
    -0.69
    POSITIVE LOGITS
     on
    1.23
     recycle
    0.81
     recycling
    0.81
    註
    0.80
     On
    0.79
     subscri
    0.76
    awake
    0.75
    on
    0.75
     Replaced
    0.73
     baron
    0.72
    Activations Density 0.004%

    No Known Activations