© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65612
    Prev
    Next
    INDEX
    Explanations

    processing tool

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

    unbiased information

    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
     potions
    0.52
     (
    0.44
     cosmetics
    0.44
     upgrading
    0.43
     ferries
    0.43
    ;
    0.42
     upgrades
    0.42
     potion
    0.42
     plantings
    0.42
    :
    0.42
    POSITIVE LOGITS
    İR
    0.52
    adă
    0.51
    гә
    0.50
    ні
    0.49
    wię
    0.49
    Nicht
    0.49
    鴳
    0.48
     উদ্দেশে
    0.47
    ডিট
    0.47
    詓
    0.47
    Activations Density 0.001%

    No Known Activations