© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19324
    Prev
    Next
    INDEX
    Explanations

    closing parentheses or braces

    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
    ɖ
    0.43
     другую
    0.42
     ८
    0.41
     ثانوي
    0.39
     %
    0.39
     "<<
    0.39
     deteriorated
    0.39
    ћ
    0.39
    鰱
    0.39
    ｐ
    0.38
    POSITIVE LOGITS
     avions
    0.46
     studierte
    0.42
    कायदा
    0.41
    ंदा
    0.41
     flies
    0.40
     adequate
    0.40
     mansions
    0.40
     capitalists
    0.39
     condos
    0.39
     espè
    0.39
    Activations Density 0.001%

    No Known Activations