© 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. 1151
    Prev
    Next
    INDEX
    Explanations

    technical terms followed by code constructs

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

    identifiers or names in code, particularly for methods, types, classes, and variables.

    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
     bolsillos
    -1.62
    今年も
    -1.40
     tatuajes
    -1.37
    僕が
    -1.34
     coûts
    -1.34
     libéral
    -1.34
    '[
    -1.32
     作り方
    -1.30
     YellowPages
    -1.29
     démoc
    -1.27
    POSITIVE LOGITS
     even
    2.41
     on
    2.03
     our
    2.00
     which
    1.99
     at
    1.97
     all
    1.95
     about
    1.73
     to
    1.68
     not
    1.65
     from
    1.63
    Activations Density 0.113%

    No Known Activations