© 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. 85661
    Prev
    Next
    INDEX
    Explanations

    or successful terrorist

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

    physical contact and animals

    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
    و
    0.53
    ו
    0.52
     misspelled
    0.50
    чным
    0.47
    o
    0.46
    િક્
    0.45
     terminado
    0.44
    ूले
    0.43
     cuando
    0.43
     maximized
    0.43
    POSITIVE LOGITS
     बतौर
    0.46
     सशस्त्र
    0.45
    릅
    0.44
    ambulance
    0.44
    ⟋
    0.44
    lé
    0.44
     उग
    0.43
     নূর
    0.43
     ಅಂಶ
    0.43
    Develop
    0.43
    Activations Density 0.001%

    No Known Activations