© 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. 197511
    Prev
    Next
    INDEX
    Explanations

    singular name

    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
    ऑनलाइन
    0.41
    étaire
    0.40
     Ở
    0.38
     Online
    0.37
    free
    0.37
     pře
    0.37
    insensitive
    0.36
    inline
    0.36
    ilateral
    0.36
     wrap
    0.36
    POSITIVE LOGITS
    OBER
    0.42
     oatmeal
    0.41
     intellig
    0.39
     collo
    0.38
     것이
    0.38
     prostat
    0.37
     Ches
    0.37
    [,-
    0.36
    NERS
    0.36
    ресень
    0.36
    Activations Density 0.002%

    No Known Activations