© 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. 10-GEMMASCOPE-RES-131K
    7. 10824
    Prev
    Next
    INDEX
    Explanations

    Andersen, Mexicana, AMC, FUNC, DESC

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

    uppercase identifiers or constants in code, particularly those ending in common programming suffixes like "_FUNC" or containing acronyms like "AMC" or "DESC".

    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
     verdaderamente
    -2.88
     Historically
    -2.83
     semelh
    -2.67
    ’
    -2.67
    并没有
    -2.66
     unending
    -2.64
     ‚
    -2.53
     Schwier
    -2.50
    .!
    -2.47
     ferocious
    -2.45
    POSITIVE LOGITS
    the
    2.94
     FUNC
    2.53
    re
    2.41
    '
    2.39
    𝐲
    2.27
    ✋
    2.20
    einander
    2.14
     siste
    2.14
    😈
    2.14
     Rakyat
    2.13
    Activations Density 0.001%

    No Known Activations