© 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. 90094
    Prev
    Next
    INDEX
    Explanations

    questions and phrases

    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
     प्रतीक
    0.44
    tragung
    0.43
    Escape
    0.43
    _.
    0.43
    )-
    0.42
     ambivalent
    0.42
    تری
    0.41
    zym
    0.41
     Escape
    0.41
     서로
    0.41
    POSITIVE LOGITS
    listen
    0.48
    iern
    0.46
    quisitos
    0.46
    等於
    0.45
    USR
    0.43
    ‌ర
    0.43
    ﻠ
    0.42
    踵
    0.42
    genre
    0.42
     নির্ম
    0.42
    Activations Density 0.003%

    No Known Activations