© 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. 85417
    Prev
    Next
    INDEX
    Explanations

    eliminates all

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

    requires spending

    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
    Negative Logits
     in
    0.59
    𝟬
    0.48
     atomically
    0.47
    iaan
    0.47
     financed
    0.46
    SIAN
    0.46
     up
    0.46
    ě
    0.46
    IDE
    0.45
     allowed
    0.45
    POSITIVE LOGITS
    식을
    0.50
     выражения
    0.47
     ዘዴ
    0.46
     উদ্ব
    0.44
     конце
    0.44
     సర
    0.44
    moires
    0.43
    calories
    0.43
     исти
    0.42
    dinner
    0.42
    Activations Density 0.001%

    No Known Activations