© 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. 107092
    Prev
    Next
    INDEX
    Explanations

    fancybox plugin

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

    guide, He lost, negates, immediately, strategically, domain, price, WWII, inspection

    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
     பரபர
    0.48
    এটা
    0.46
    a
    0.45
    妷
    0.45
    มัน
    0.44
    Kong
    0.44
    crime
    0.44
    ء
    0.44
    AUTH
    0.43
    DETAIL
    0.43
    POSITIVE LOGITS
    isty
    0.47
    ieni
    0.47
     化粧
    0.47
    ably
    0.47
    ilib
    0.47
    mtq
    0.47
     posts
    0.46
     posted
    0.46
    anced
    0.46
     tamp
    0.46
    Activations Density 0.001%

    No Known Activations