© 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. 103830
    Prev
    Next
    INDEX
    Explanations

    code and operators

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

    comparison operators or equality symbols in code (like `==`, `=`, `|`, `:` in conditional expressions).

    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
    This
    -2.30
    They
    -2.17
    3
    -2.03
    9
    -1.97
    2
    -1.95
    We
    -1.95
    Semua
    -1.93
    RTHOOK
    -1.92
     Though
    -1.91
     Даже
    -1.91
    POSITIVE LOGITS
     plenamente
    1.80
     viaja
    1.79
    遑
    1.78
     trzec
    1.74
     poderos
    1.74
     that
    1.70
     tomando
    1.65
    '
    1.62
     verschillende
    1.60
     variados
    1.60
    Activations Density 0.059%

    No Known Activations