© 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. 131523
    Prev
    Next
    INDEX
    Explanations

    removal, type, waste, overlooked, pace

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

    authors' intentions

    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
    i
    0.62
    p
    0.61
    reduce
    0.60
    rs
    0.59
    ms
    0.56
    ins
    0.55
    an
    0.54
    you
    0.54
    a
    0.54
    in
    0.53
    POSITIVE LOGITS
     وړاند
    0.46
     이슈
    0.46
    埕
    0.46
    谘
    0.45
    栊
    0.45
    輋
    0.45
     تحقیق
    0.45
    缡
    0.44
    ছে
    0.43
     الزام
    0.43
    Activations Density 0.000%

    No Known Activations