© 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. 119865
    Prev
    Next
    INDEX
    Explanations

    code or variable names

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

    opening parentheses in function calls.

    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
    </h2>
    -1.69
     is
    -1.49
    Chaque
    -1.30
    OREM
    -1.29
    档案馆
    -1.29
     吧
    -1.27
     by
    -1.27
     啦
    -1.23
     comienza
    -1.22
    Vendredi
    -1.22
    POSITIVE LOGITS
     that
    1.42
     then
    1.39
     your
    1.36
    Regressor
    1.35
    //
    1.34
    ivant
    1.34
    であり
    1.32
     русских
    1.32
     mitään
    1.32
     kompres
    1.30
    Activations Density 0.030%

    No Known Activations