© 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. 22-GEMMASCOPE-RES-131K
    7. 128329
    Prev
    Next
    INDEX
    Explanations

    delete

    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_22/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
    vání
    -0.96
     Gastroenter
    -0.94
     makeup
    -0.94
     Pozna
    -0.92
     poliester
    -0.90
    ometrial
    -0.90
    FDA
    -0.89
     Hift
    -0.87
    넨
    -0.87
     turun
    -0.86
    POSITIVE LOGITS
    最後は
    0.96
     de
    0.85
    FileUtil
    0.84
     edildi
    0.79
     古着
    0.79
     outright
    0.77
    了不少
    0.77
    最后一个
    0.76
    婆婆
    0.76
     delete
    0.76
    Activations Density 0.008%

    No Known Activations