© 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. 102058
    Prev
    Next
    INDEX
    Explanations

    court case citations

    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
     to
    -2.41
     and
    -2.13
    および
    -1.92
     çerçe
    -1.80
     by
    -1.79
     or
    -1.75
     哪些
    -1.74
     But
    -1.70
    %.
    -1.67
    </u>
    -1.66
    POSITIVE LOGITS
    c
    2.27
    ،
    2.09
    ção
    1.85
     ۵
    1.83
    b
    1.82
    栳
    1.80
     ホルダー
    1.75
     ค
    1.75
    llten
    1.74
     ofere
    1.73
    Activations Density 0.004%

    No Known Activations