© 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. 16410
    Prev
    Next
    INDEX
    Explanations

    time spent reading

    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
    로그
    0.41
    numericUpDown
    0.41
    кономі
    0.39
    Workshop
    0.39
    fdata
    0.39
    디
    0.39
     fér
    0.38
     damage
    0.37
     ಅಲ
    0.37
    сподар
    0.37
    POSITIVE LOGITS
     阅读
    0.57
     पढ़ने
    0.57
    阅读
    0.55
     статьи
    0.53
    閱讀
    0.51
     reading
    0.50
     पढ़ने
    0.49
    読む
    0.49
     lettura
    0.49
     읽
    0.48
    Activations Density 0.048%

    No Known Activations