© 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. 117785
    Prev
    Next
    INDEX
    Explanations

    taxes due

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

    Series Matters

    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
    dashboard
    0.50
     tubules
    0.48
     monasteries
    0.47
    UserService
    0.47
    GEN
    0.45
    स्टल
    0.45
    कविता
    0.45
    
    0.45
    WISE
    0.45
    GINIA
    0.44
    POSITIVE LOGITS
    ijn
    0.58
     আক্রমণের
    0.53
     يد
    0.52
     الحرب
    0.51
    stylesheet
    0.46
     auteur
    0.46
     rhetoric
    0.45
    ו
    0.45
     அங்க
    0.45
     ނ
    0.45
    Activations Density 0.001%

    No Known Activations