© 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. 128520
    Prev
    Next
    INDEX
    Explanations

    Championship Vinyl, Turbulent Identity

    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
    il
    0.73
    ’
    0.61
    on
    0.57
    os
    0.57
    1
    0.55
    ed
    0.54
    ic
    0.53
    time
    0.53
    oon
    0.52
    as
    0.52
    POSITIVE LOGITS
    ㅕ
    0.48
    🎗
    0.47
    🦇
    0.47
     Echt
    0.46
    Ꮺ
    0.46
    示す
    0.46
    trashItem
    0.44
    ప్పు
    0.44
    ℑ
    0.44
    ጕ
    0.43
    Activations Density 0.001%

    No Known Activations