© 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. 78167
    Prev
    Next
    INDEX
    Explanations

    units of measure

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

    hardware, equipment, calculations

    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
     stands
    0.46
    acariy
    0.45
     vya
    0.43
    hôpital
    0.43
    kaisi
    0.43
    䏹
    0.43
     grieving
    0.42
     कुर्सी
    0.42
     உண்டு
    0.42
     pregnant
    0.42
    POSITIVE LOGITS
    ↵
    0.44
    시
    0.42
    if
    0.42
    螨
    0.41
    免费
    0.40
     MOTOR
    0.39
    تميز
    0.39
    ﺠ
    0.39
    إن
    0.38
    تا
    0.38
    Activations Density 0.002%

    No Known Activations