© 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. 205201
    Prev
    Next
    INDEX
    Explanations

    Moroccan palace

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

    Inflation Hedge

    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
    创作
    0.51
     सूफ़ी
    0.50
    冂
    0.47
    鲛
    0.47
     séries
    0.47
     pensé
    0.46
     comenzamos
    0.46
    组织
    0.46
    ुणा
    0.45
     frontière
    0.45
    POSITIVE LOGITS
     contactless
    0.49
     unbeatable
    0.46
    ird
    0.44
    verified
    0.44
     homeowner
    0.43
    既に
    0.43
     लाभार्थियों
    0.43
     П
    0.43
     consolidated
    0.42
    п
    0.42
    Activations Density 0.001%

    No Known Activations