© 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. 10-GEMMASCOPE-RES-131K
    7. 104924
    Prev
    Next
    INDEX
    Explanations

    underscore prefix or separator

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

    underscores in variable names, function names, and identifiers in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     "
    -2.41
    a
    -2.27
    饪
    -2.19
     viewed
    -2.05
     be
    -2.03
     to
    -2.03
     he
    -2.03
     In
    -2.02
    があります
    -1.95
    s
    -1.94
    POSITIVE LOGITS
    ’,
    2.92
    lgari
    2.75
    逦
    2.67
    ㈮
    2.63
    伱
    2.59
    ,’
    2.55
     melap
    2.45
     renown
    2.44
    鍇
    2.42
     mengucap
    2.39
    Activations Density 0.004%

    No Known Activations