© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9047
    Prev
    Next
    INDEX
    Explanations

    board initialization or game structure

    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
     而
    -1.97
     but
    -1.85
    vantaged
    -1.83
    </h4>
    -1.77
    硨
    -1.73
    </h5>
    -1.69
     to
    -1.68
    咴
    -1.60
    </td>
    -1.59
    
    -1.59
    POSITIVE LOGITS
    <bos>
    2.13
    𓋼
    2.05
    Most
    2.03
     inteligentes
    2.00
    互動
    1.92
     nasional
    1.90
    With
    1.88
     recurrir
    1.88
    時間の
    1.83
    ๋า
    1.82
    Activations Density 0.004%

    No Known Activations