© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4523
    Prev
    Next
    INDEX
    Explanations

    non- english characters or abbreviations

    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_65k_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
     with
    0.82
     (
    0.72
     at
    0.69
     a
    0.68
     by
    0.63
    with
    0.58
     for
    0.57
     on
    0.51
    at
    0.51
     of
    0.50
    POSITIVE LOGITS
    quele
    0.73
    س
    0.63
    ла
    0.58
    ला
    0.57
    ре
    0.56
    و
    0.55
    д
    0.54
    ेल
    0.52
    عنی
    0.52
    ري
    0.52
    Activations Density 0.201%

    No Known Activations