© 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. 84497
    Prev
    Next
    INDEX
    Explanations

    describing technology

    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
    。」
    -1.89
    ！！！！
    -1.77
     kön
    -1.75
    ！（
    -1.68
    ？（
    -1.63
    ！"
    -1.58
     разом
    -1.56
    哟
    -1.56
    '
    -1.55
    狃
    -1.55
    POSITIVE LOGITS
    .
    2.52
     achten
    2.17
    </h4>
    2.08
     to
    2.05
    </sup>
    2.00
     vollständ
    1.85
     persönlichen
    1.85
     mittlerweile
    1.82
    xelles
    1.81
     geringen
    1.81
    Activations Density 0.039%

    No Known Activations