© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 34323
    Prev
    Next
    INDEX
    Explanations

    8 plan

    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_all/layer_41_width_262k_l0_big
    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
     weißen
    0.43
     الرغم
    0.41
    зер
    0.40
     उगा
    0.40
     眼
    0.40
    rneğin
    0.39
    तरीय
    0.38
     gamble
    0.38
     gamb
    0.38
     дости
    0.38
    POSITIVE LOGITS
    in
    0.49
    on
    0.47
    იშ
    0.45
    is
    0.43
    ajada
    0.43
    isht
    0.41
    an
    0.40
    ח
    0.40
    elio
    0.40
    Tokyo
    0.39
    Activations Density 0.003%

    No Known Activations