© 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. 58055
    Prev
    Next
    INDEX
    Explanations

    names, incidents, or businesses

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

    kind of character

    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
     생
    0.48
    는
    0.47
     animal
    0.46
     termites
    0.45
     peers
    0.45
     หา
    0.45
    bbi
    0.45
     攵
    0.44
     사용
    0.44
    ;.
    0.44
    POSITIVE LOGITS
    金を
    0.45
    businesses
    0.44
    事件
    0.44
    Businesses
    0.44
    幇
    0.43
    キャラクター
    0.42
    指導
    0.41
     घटनाओं
    0.41
     Businesses
    0.41
    起動
    0.41
    Activations Density 0.000%

    No Known Activations