© 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. 78840
    Prev
    Next
    INDEX
    Explanations

    emanates from

    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
    IK
    0.46
    ೇಶ್
    0.46
     وړ
    0.45
    也很
    0.44
    快樂
    0.44
    鈈
    0.44
    वड
    0.43
    اي
    0.43
     ਹੀ
    0.43
     खेल
    0.43
    POSITIVE LOGITS
     a
    0.52
    '
    0.46
     v
    0.46
    โยชน์
    0.44
     doctorate
    0.43
     even
    0.43
     n
    0.43
     stati
    0.43
     mus
    0.43
    lds
    0.42
    Activations Density 0.002%

    No Known Activations