© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11903
    Prev
    Next
    INDEX
    Explanations

    programming questions and media names

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

    the token "org" at the beginning of Java package names or organizational domains.

    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
    ٧
    -1.88
     renforcé
    -1.87
     juſ
    -1.77
    냑
    -1.77
     vack
    -1.73
    呖
    -1.72
     organisme
    -1.69
     éclairage
    -1.66
    蓠
    -1.63
     basé
    -1.63
    POSITIVE LOGITS
     in
    2.64
     at
    2.23
     with
    2.20
     all
    2.08
     when
    1.85
     from
    1.75
     out
    1.73
     before
    1.72
     be
    1.67
     should
    1.66
    Activations Density 0.000%

    No Known Activations