© 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. 86891
    Prev
    Next
    INDEX
    Explanations

    starting with sco

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

    The neuron detects occurrences of the sub‐string “sco” (tokens starting with “sco,” such as sco, scope, scoping, SCO, 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
     geisti
    -0.78
    cetos
    -0.73
     więc
    -0.72
     Sandberg
    -0.71
     Effekt
    -0.71
     betreffenden
    -0.70
    flor
    -0.69
    綵
    -0.69
     contactar
    -0.69
    بحث
    -0.68
    POSITIVE LOGITS
     sco
    1.50
     Sco
    1.45
    sco
    1.25
    スコ
    1.23
     SCO
    1.20
    Sco
    1.12
     ско
    1.04
    СКО
    0.97
     Ско
    0.93
    SCO
    0.89
    Activations Density 0.016%

    No Known Activations