© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118370
    Prev
    Next
    INDEX
    Explanations

    legal and code filings

    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_34/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
     torchvision
    -0.79
     withRouter
    -0.76
    bParam
    -0.76
     Conexion
    -0.75
    boldsymbol
    -0.75
    доры
    -0.74
    oxo
    -0.73
    ssymb
    -0.71
    Sept
    -0.70
    裁判
    -0.70
    POSITIVE LOGITS
    Nino
    0.86
    Tori
    0.86
    יטה
    0.84
    Rena
    0.84
    igur
    0.82
    adalupe
    0.80
    مشخص
    0.77
     Tori
    0.77
    Marry
    0.77
     negativos
    0.77
    Activations Density 0.002%

    No Known Activations