© 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. 125990
    Prev
    Next
    INDEX
    Explanations

    partially paved, then you, should be, path

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

    compensation, benefits, operator, upwards, game, Uncle, Answer

    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
     hjälp
    0.55
    يمان
    0.50
    ،
    0.49
     با
    0.48
    ۔
    0.47
     แต
    0.46
     موت
    0.46
     شف
    0.45
    عم
    0.45
     عليك
    0.44
    POSITIVE LOGITS
    ↵↵↵↵↵↵
    0.53
    ↵↵↵↵↵
    0.53
    ↵↵↵↵↵↵↵
    0.47
    <0x0D>
    0.45
    PEC
    0.44
    ↵↵↵↵↵↵↵↵
    0.44
    TERM
    0.44
     Bentham
    0.43
    ↵↵↵
    0.43
     RE
    0.43
    Activations Density 0.002%

    No Known Activations