© 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. 123796
    Prev
    Next
    INDEX
    Explanations

    crustal, crustacean, crusting

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

    references to "crust" in geological, biological, and food contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    我們
    -3.44
    焢
    -2.91
    鹩
    -2.86
     Historically
    -2.56
    薷
    -2.55
     We
    -2.45
    鴴
    -2.45
    いいのか
    -2.34
     Occasionally
    -2.31
    並不
    -2.31
    POSITIVE LOGITS
    ↵
    2.36
    ();
    2.34
    ：[
    2.33
    寕
    2.33
    ⃚
    2.27
    ,"
    2.23
    ’
    2.22
    蠖
    2.22
    ；
    2.22
    );
    2.20
    Activations Density 0.002%

    No Known Activations