© 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. 166606
    Prev
    Next
    INDEX
    Explanations

    contrast and exceptions

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

    library burning

    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
    ᱟ
    0.55
    льности
    0.52
     naranja
    0.52
    規
    0.50
    क्षा
    0.48
     manzana
    0.48
    ળા
    0.48
     билет
    0.47
     Ξ
    0.47
    ‌هایی
    0.47
    POSITIVE LOGITS
    ive
    0.60
    kal
    0.49
    ume
    0.47
    bym
    0.46
    inton
    0.46
    thand
    0.46
    iselt
    0.45
    waite
    0.45
    ion
    0.44
    thick
    0.44
    Activations Density 0.000%

    No Known Activations