© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32919
    Prev
    Next
    INDEX
    Explanations

    not all or not the same

    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
    HASAN
    -0.98
     pprint
    -0.93
     alltid
    -0.91
     fileSize
    -0.90
     will
    -0.90
     primacy
    -0.89
     needs
    -0.88
    gypten
    -0.87
     سانتی
    -0.84
     predicting
    -0.82
    POSITIVE LOGITS
     bad
    0.92
    Související
    0.91
     بسیاری
    0.89
    caric
    0.84
    Representative
    0.84
    Separ
    0.84
    extrême
    0.82
     winked
    0.81
     fakty
    0.81
    mäßige
    0.81
    Activations Density 0.048%

    No Known Activations