© 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. 25946
    Prev
    Next
    INDEX
    Explanations

    URLs and data fields

    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
     will
    -1.06
     hålla
    -1.04
    агностика
    -1.01
     hilsen
    -1.00
     varje
    -0.97
    чен
    -0.96
     nästa
    -0.96
     śpiew
    -0.95
     förra
    -0.94
     framför
    -0.93
    POSITIVE LOGITS
    たび
    1.17
    ⅙
    1.14
    ⅝
    1.10
    剮
    1.00
     detalhe
    1.00
    ⅞
    0.96
     slou
    0.96
    ⅗
    0.93
    ⅖
    0.93
    ございました
    0.93
    Activations Density 0.016%

    No Known Activations