© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39131
    Prev
    Next
    INDEX
    Explanations

    cause and origin

    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
    mographie
    -1.02
    🐐
    -1.01
     betek
    -0.97
    woord
    -0.96
    idends
    -0.95
     tertawa
    -0.95
     jäsen
    -0.94
    וּ
    -0.94
     for
    -0.93
     দেখ
    -0.93
    POSITIVE LOGITS
    我已经
    1.34
     recent
    1.20
     from
    1.20
    recent
    1.15
     previously
    1.13
     previous
    1.13
    していない
    1.09
     blivit
    1.09
     recientes
    1.09
     ранее
    1.07
    Activations Density 0.038%

    No Known Activations