© 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. 100372
    Prev
    Next
    INDEX
    Explanations

    madness

    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
    </h3>
    -3.17
     decidido
    -2.83
     comprado
    -2.47
    ."));
    -2.39
    比特币
    -2.38
    
    -2.33
    褙
    -2.31
    ୈ
    -2.31
    🥳
    -2.28
    鮠
    -2.27
    POSITIVE LOGITS
    </b>
    4.31
    .
    3.70
    section
    2.75
    <i>
    2.69
    4
    2.66
    We
    2.58
    ка
    2.56
    7
    2.53
    6
    2.50
    But
    2.48
    Activations Density 0.003%

    No Known Activations