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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129120
    Prev
    Next
    INDEX
    Explanations

    jolly followed by names or places

    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
    ：“
    -3.03
    ?”
    -3.03
    ，“
    -3.00
    </b>
    -2.88
    、“
    -2.78
    鷓
    -2.72
    </h5>
    -2.69
    柃
    -2.67
    be
    -2.67
    忸
    -2.61
    POSITIVE LOGITS
    謌
    2.77
    谖
    2.77
    ية
    2.69
     ་
    2.66
    </strong>
    2.56
    蹋
    2.56
    菹
    2.42
    廰
    2.41
     combustível
    2.39
     інші
    2.36
    Activations Density 0.015%

    No Known Activations