© 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-262K
    7. 139486
    Prev
    Next
    INDEX
    Explanations

    Adopt Reset additions usually Market

    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
     vandalism
    0.46
     universe
    0.45
     Архивная
    0.45
    សម្រាប់ការ
    0.44
     matrix
    0.44
     Hulk
    0.43
    ኝ
    0.43
    作为一个
    0.42
     catchment
    0.42
     develop
    0.42
    POSITIVE LOGITS
    ören
    0.50
    qu
    0.48
    elace
    0.47
    announce
    0.46
    '
    0.45
    ít
    0.45
    ul
    0.44
    ir
    0.44
    aq
    0.43
    ör
    0.43
    Activations Density 0.003%

    No Known Activations