© 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. 503
    Prev
    Next
    INDEX
    Explanations

    mercedes and xbox

    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
    </strong>
    -2.89
    垍
    -2.67
    컫
    -2.56
    甚至是
    -2.50
    ください
    -2.30
    ков
    -2.23
    n
    -2.20
     anche
    -2.16
     you
    -2.16
     furthermore
    -2.14
    POSITIVE LOGITS
    我們
    2.83
    which
    2.61
    ’
    2.34
    from
    2.34
    趼
    2.33
    艫
    2.30
    狆
    2.19
    低声
    2.17
     紀
    2.17
     現貨
    2.16
    Activations Density 0.002%

    No Known Activations