© 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. 201714
    Prev
    Next
    INDEX
    Explanations

    items like apple, threat, ingredient, claw, workspace, details, substring

    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
    模拟
    0.48
     केक
    0.47
    删除
    0.47
    క్ష
    0.45
    ள்ப
    0.45
    ╯
    0.44
     Costello
    0.42
     FORD
    0.42
    ன்றும்
    0.42
    দশ
    0.42
    POSITIVE LOGITS
     of
    0.66
    of
    0.56
     납
    0.49
    のリ
    0.48
     exemplify
    0.47
    ag
    0.46
    ኛውም
    0.46
    iat
    0.45
    aj
    0.45
    ของ
    0.44
    Activations Density 0.000%

    No Known Activations