© 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. 62240
    Prev
    Next
    INDEX
    Explanations

    William Hill, Coinbase, League of Legends

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

    units of quantity or relation

    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
    ра
    0.58
    дев
    0.45
    рин
    0.44
    ۵
    0.42
    ♤
    0.42
    বল
    0.41
    ०
    0.40
    лил
    0.40
     plump
    0.38
    objectif
    0.38
    POSITIVE LOGITS
    czych
    0.41
     Troll
    0.40
    体
    0.40
     Holland
    0.40
     ausencia
    0.39
    Charting
    0.39
    徹
    0.39
    ↵↵↵
    0.39
    上海
    0.38
    倡
    0.38
    Activations Density 0.000%

    No Known Activations