© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 191352
    Prev
    Next
    INDEX
    Explanations

    specifically designed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Game
    0.42
    ;%%
    0.42
    immer
    0.42
    Domain
    0.41
    String
    0.39
    zoo
    0.39
    Yosh
    0.38
    ](../../
    0.38
    %]
    0.38
    gender
    0.38
    POSITIVE LOGITS
     cic
    0.43
     опо
    0.43
    ۇل
    0.42
     TRPV
    0.42
     Lune
    0.42
     moths
    0.40
     CIC
    0.39
     centralised
    0.39
     tipe
    0.38
     nokta
    0.38
    Activations Density 0.004%

    No Known Activations