© 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. 102715
    Prev
    Next
    INDEX
    Explanations

    embedded programming functions

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

    The neuron flags programming‐language keywords and function declarations (e.g. “function,” “void,” “setup,” “loop,” etc.).

    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
     renovate
    -0.77
     Luk
    -0.71
     Cooke
    -0.71
     Jones
    -0.71
     mature
    -0.70
     Durant
    -0.70
     endgame
    -0.70
     predominate
    -0.70
     Jung
    -0.69
    TAGE
    -0.69
    POSITIVE LOGITS
     keyPressed
    0.92
    drawSprites
    0.88
     setup
    0.79
     블
    0.79
     draw
    0.78
    ismen
    0.77
    delingen
    0.77
     Архиви
    0.76
    preload
    0.75
     menjual
    0.75
    Activations Density 0.017%

    No Known Activations