© 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. 22-GEMMASCOPE-RES-131K
    4. 68353
    Prev
    Next
    INDEX
    Explanations

    language-specific prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    <bos>
    -2.86
     οποία
    -2.06
    vereign
    -1.95
    คุณ
    -1.95
    を
    -1.95
    輒
    -1.92
    軼
    -1.91
    谕
    -1.90
    方針
    -1.88
    vereignty
    -1.85
    POSITIVE LOGITS
    ふと
    2.42
    際に
    2.39
     mutta
    2.36
    ほら
    2.27
    感じで
    2.27
    んですよ
    2.23
    ものである
    2.16
    ところに
    2.13
    あぁ
    2.11
    おわりに
    2.09
    Activations Density 0.000%

    No Known Activations