© 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. 22174
    Prev
    Next
    INDEX
    Explanations

    deliver speech or message

    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
     остальных
    -2.14
    能让
    -1.91
     sechs
    -1.83
     ")[
    -1.79
     circumstances
    -1.71
     шесть
    -1.69
     innych
    -1.67
    0
    -1.66
     третье
    -1.65
     reír
    -1.63
    POSITIVE LOGITS
     Affaires
    1.69
    неров
    1.52
    RMB
    1.48
    悒
    1.46
     heet
    1.46
    ragamo
    1.46
    
    1.46
     créations
    1.45
    летия
    1.45
    ⼠
    1.43
    Activations Density 0.030%

    No Known Activations