© 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. 68208
    Prev
    Next
    INDEX
    Explanations

    door features and contexts

    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
    ﾏ
    -2.94
    屺
    -2.91
    ｱ
    -2.83
     erectile
    -2.64
     尔
    -2.64
    vantaged
    -2.64
     الخارجية
    -2.63
    鯢
    -2.61
     galinha
    -2.61
     sœurs
    -2.59
    POSITIVE LOGITS
    ra
    4.13
    ра
    3.27
     They
    2.94
     Likewise
    2.89
     colectiva
    2.78
    趼
    2.73
    la
    2.63
     Their
    2.55
     Similarly
    2.52
    ';
    2.48
    Activations Density 0.012%

    No Known Activations