© 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. 174021
    Prev
    Next
    INDEX
    Explanations

    first inspections

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

    Norepinephrine, time taken, car theft

    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
     completos
    0.54
    opl
    0.54
    va
    0.51
    n
    0.51
    ok
    0.50
    ies
    0.49
    :}
    0.49
    o
    0.48
    ud
    0.48
     excelentes
    0.48
    POSITIVE LOGITS
     рай
    0.45
     breeding
    0.43
     pathogenesis
    0.43
     यातायात
    0.43
     prosecuting
    0.43
     रजिस्ट्री
    0.43
     Visitation
    0.43
     نت
    0.42
     राजनीति
    0.42
     ہی
    0.42
    Activations Density 0.001%

    No Known Activations