© 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. 4738
    Prev
    Next
    INDEX
    Explanations

    average, total, percent

    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
    学习
    0.50
    فهام
    0.50
    逻
    0.50
    帮忙
    0.48
    谔
    0.47
     pembelajaran
    0.47
     학습
    0.47
     apprendre
    0.47
     pédagog
    0.46
    客观
    0.46
    POSITIVE LOGITS
    average
    0.69
     averages
    0.66
    total
    0.66
     total
    0.64
     average
    0.64
     overall
    0.64
    %
    0.63
    overall
    0.61
    percent
    0.58
     percentages
    0.57
    Activations Density 0.214%

    No Known Activations