© 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. 77393
    Prev
    Next
    INDEX
    Explanations

    visual suppression

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

    breadth of knowledge

    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
     পৃথিবী
    0.51
    subtree
    0.50
     பூம
    0.50
    㛣
    0.49
     热
    0.48
    大地
    0.48
     वृद्धि
    0.47
     ഭൂ
    0.47
     则
    0.47
    踉
    0.47
    POSITIVE LOGITS
     initialize
    0.55
     handles
    0.52
     handle
    0.47
     WASH
    0.47
     Identifier
    0.46
    >
    0.46
     holds
    0.46
     header
    0.46
     normally
    0.46
     as
    0.45
    Activations Density 0.001%

    No Known Activations