© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 41352
    Prev
    Next
    INDEX
    Explanations

    common misconceptions, movies, flow, set, tubes

    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
    M
    0.60
     V
    0.56
     Av
    0.56
     J
    0.55
    K
    0.55
     M
    0.54
    في
    0.52
     B
    0.51
     H
    0.50
    of
    0.50
    POSITIVE LOGITS
     배웠
    0.53
     bitOp
    0.52
     belajar
    0.52
    <unused1014>
    0.52
     छोड़
    0.51
     музи
    0.50
    isière
    0.50
     caldo
    0.49
    َان
    0.49
    <unused390>
    0.49
    Activations Density 0.001%

    No Known Activations