© 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. 181107
    Prev
    Next
    INDEX
    Explanations

    bridesmaid dresses

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

    need, require, must, skill, time

    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
     general
    0.45
     prudent
    0.43
     pur
    0.42
    nite
    0.42
     prud
    0.41
     [
    0.40
    ↵
    0.40
     generale
    0.40
    ceptive
    0.39
     Griffith
    0.39
    POSITIVE LOGITS
    স
    0.71
    ম
    0.69
    ক
    0.57
    ק
    0.57
    ח
    0.57
    ବ
    0.55
    Қ
    0.54
    बॉलीवुड
    0.54
     автофо
    0.54
     étant
    0.52
    Activations Density 0.001%

    No Known Activations