© 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. 72661
    Prev
    Next
    INDEX
    Explanations

    authorize

    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
    ,\\
    -2.17
    \\
    -2.02
    ’
    -2.00
    ,...
    -1.95
     Of
    -1.94
     verknüp
    -1.89
    ，「
    -1.88
    </h2>
    -1.88
    ll
    -1.87
    )
    -1.85
    POSITIVE LOGITS
    嚕
    2.27
    
    2.27
    された
    2.08
    の人生
    2.05
     of
    2.03
    颳
    2.03
    になりますが
    1.98
    經歷
    1.98
    過來
    1.97
    擔任
    1.96
    Activations Density 0.021%

    No Known Activations