© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 112334
    Prev
    Next
    INDEX
    Explanations

    phrases starting with sign, legally, incomplete, Tapatalk, what

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

    positive trajectory

    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
     ホワイト
    0.47
    未來
    0.46
     東京都
    0.45
     ガラス
    0.45
     WINDOW
    0.44
     個
    0.44
     市場
    0.44
     iframe
    0.44
     undersea
    0.43
     WEB
    0.43
    POSITIVE LOGITS
    ör
    0.46
    璎
    0.46
    lekt
    0.46
     протяжении
    0.45
    最为
    0.45
    ael
    0.44
     причиной
    0.42
     প্রতিনি
    0.42
    adio
    0.42
    Expressions
    0.42
    Activations Density 0.002%

    No Known Activations