© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 134616
    Prev
    Next
    INDEX
    Explanations

    languages and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    sequence, matrix, pandemic, calculator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    เกี่ยว
    0.53
    Ժ
    0.52
    鈳
    0.49
     Timeline
    0.47
     哦
    0.47
    hā
    0.47
    变化的
    0.47
    các
    0.46
    炰
    0.46
    Ivy
    0.45
    POSITIVE LOGITS
     حکمت
    0.54
     clenched
    0.53
     untreated
    0.48
     فارس
    0.47
     ragged
    0.46
     ብ
    0.46
    ernet
    0.45
     charted
    0.45
     Biophys
    0.44
     ची
    0.43
    Activations Density 0.000%

    No Known Activations