© 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. 9134
    Prev
    Next
    INDEX
    Explanations

    fact that

    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
    锖
    -2.42
    汌
    -2.33
    держание
    -2.31
    푘
    -2.14
    Ⅱ
    -2.09
    迓
    -2.09
    ?’
    -2.08
    
    -2.03
    荩
    -2.02
    嚶
    -2.00
    POSITIVE LOGITS
     that
    4.41
    <td>
    2.77
    
    2.67
    ﹍﹍
    2.31
     consegui
    2.16
    鳐
    2.14
    which
    2.09
    龊
    2.08
     bedienen
    2.02
     judicia
    1.98
    Activations Density 0.023%

    No Known Activations