© 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-65K
    7. 46468
    Prev
    Next
    INDEX
    Explanations

    from another

    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
    执行
    0.49
     भेड़
    0.45
     بے
    0.43
     눈
    0.43
     문자
    0.43
     빛
    0.42
     ትንሽ
    0.41
    effetto
    0.41
    ้องกัน
    0.41
     키
    0.41
    POSITIVE LOGITS
     in
    0.52
    '
    0.49
     of
    0.47
     started
    0.47
    Наи
    0.46
     enter
    0.45
     From
    0.44
     a
    0.43
    com
    0.43
     upl
    0.43
    Activations Density 0.003%

    No Known Activations