© 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. 31-GEMMASCOPE-2-RES-262K
    7. 79751
    Prev
    Next
    INDEX
    Explanations

    technical, scientific, and descriptive terms

    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_31_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
     Ansprüche
    0.51
    രു
    0.48
     Vereinigten
    0.47
    新聞
    0.46
    黒
    0.46
     तर
    0.44
     hongkong
    0.44
    よい
    0.44
    山口
    0.44
     YouTuber
    0.44
    POSITIVE LOGITS
     extraordinarily
    0.48
    Circle
    0.44
     extraordin
    0.43
     unfolds
    0.43
    ia
    0.42
    ::-
    0.42
    !-
    0.42
     illuminates
    0.41
    aths
    0.41
    or
    0.41
    Activations Density 0.007%

    No Known Activations