© 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. 129242
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
    嘮
    -0.86
     税
    -0.85
    全体の
    -0.83
     assistência
    -0.83
     magi
    -0.82
     Ever
    -0.82
    这让
    -0.82
    思います
    -0.80
     Aldi
    -0.79
     overall
    -0.79
    POSITIVE LOGITS
     or
    1.73
     или
    1.00
    或
    0.96
    冰冷
    0.96
    或是
    0.94
     或
    0.91
    或者
    0.90
    ilados
    0.86
     veya
    0.83
    kých
    0.83
    Activations Density 0.014%

    No Known Activations