© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 593
    Prev
    Next
    INDEX
    Explanations

    Shea, Shu, Lili names

    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_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
    ).
    -3.44
    ing
    -3.28
    );
    -3.19
    ↵↵
    -2.95
    }$
    -2.88
     -
    -2.77
    $.
    -2.72
    }{
    -2.66
     Only
    -2.64
    ed
    -2.55
    POSITIVE LOGITS
    棡
    2.84
    螄
    2.81
    䛗
    2.73
    ѣмъ
    2.63
     parfü
    2.47
     bluza
    2.47
    🫴
    2.44
    鹬
    2.42
    ỽ
    2.41
    蟊
    2.41
    Activations Density 0.016%

    No Known Activations