© 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. 59534
    Prev
    Next
    INDEX
    Explanations

    racism

    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
    ญี่ป
    -2.91
    哢
    -2.45
    。】
    -2.31
    崐
    -2.31
    难怪
    -2.30
    
    -2.25
    </h2>
    -2.22
    妘
    -2.19
    先は
    -2.17
    焌
    -2.17
    POSITIVE LOGITS
    .
    2.58
    >
    2.53
    та
    2.42
    轻声
    2.16
     местах
    2.11
    ਃ
    2.11
    }$
    2.08
    お楽しみに
    2.06
    C
    2.06
    N
    2.05
    Activations Density 0.004%

    No Known Activations