© 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. 8770
    Prev
    Next
    INDEX
    Explanations

    return, refund, redistribution, reproduction, second hand

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

    distributions and licenses

    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
    ʢ
    0.38
    给了
    0.33
    𝟭
    0.33
    ologisk
    0.32
    ställ
    0.31
    getDate
    0.31
    Databaze
    0.31
    ılığı
    0.31
    ji
    0.31
    datat
    0.31
    POSITIVE LOGITS
     sows
    0.35
     sailboat
    0.32
     Rhodesia
    0.32
    胚
    0.31
     mitochondrial
    0.31
     sail
    0.31
     busque
    0.30
     Drosophila
    0.30
     linemen
    0.30
     deformed
    0.30
    Activations Density 0.000%

    No Known Activations