© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151154
    Prev
    Next
    INDEX
    Explanations

    Adjunct Professor

    np_acts-logits-general · gemini-2.5-flash-lite

    predicting differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    バリー
    0.51
    ྒ
    0.48
     youngster
    0.45
    Stanley
    0.43
    酵
    0.43
    ヌ
    0.43
    */
    0.42
    igui
    0.42
     dịp
    0.41
     fledgling
    0.41
    POSITIVE LOGITS
    kosten
    0.48
    滖
    0.48
    ers
    0.47
    рова
    0.46
     கடந்த
    0.43
    isks
    0.43
     Trap
    0.42
    vänd
    0.42
    ression
    0.41
     전략
    0.41
    Activations Density 0.001%

    No Known Activations