© 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. 99323
    Prev
    Next
    INDEX
    Explanations

    same year, collection of

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

    discrete concepts

    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
    рис
    0.48
     trou
    0.47
     como
    0.45
     scriv
    0.45
     procédé
    0.44
     pisc
    0.44
    нон
    0.44
    и
    0.43
     stran
    0.42
     hendak
    0.42
    POSITIVE LOGITS
     बचाया
    0.53
     Offences
    0.50
     हटाया
    0.50
     Gardening
    0.49
    逺
    0.48
     మరింత
    0.48
     Aging
    0.46
     особли
    0.46
     উপে
    0.46
     Plugins
    0.45
    Activations Density 0.000%

    No Known Activations