© 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. 201212
    Prev
    Next
    INDEX
    Explanations

    assigning code from word sequence

    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
    ﻦ
    0.49
    బ్యా
    0.49
    色列
    0.49
    Twilight
    0.48
    思考
    0.46
    ס
    0.46
    莪
    0.45
    PAS
    0.45
    Rails
    0.45
    怎樣
    0.45
    POSITIVE LOGITS
     on
    0.48
     powied
    0.48
     [...
    0.44
     and
    0.44
     TikTok
    0.43
     Maxine
    0.43
     Judd
    0.42
     Moot
    0.42
     Jud
    0.42
     Sony
    0.41
    Activations Density 0.005%

    No Known Activations