© 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. 63057
    Prev
    Next
    INDEX
    Explanations

    recognizes students or achievement

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

    falling unconscious

    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
    حان
    0.48
     excepción
    0.46
    瑪
    0.45
    ખા
    0.45
     pengaturan
    0.45
     кори
    0.45
     conocidas
    0.44
     preferencias
    0.44
     उग
    0.44
     colorido
    0.44
    POSITIVE LOGITS
    ed
    0.52
    F
    0.52
     pledges
    0.51
     journalists
    0.50
     Debt
    0.50
     characters
    0.48
     Salaries
    0.48
     Nass
    0.48
     Phase
    0.47
     artists
    0.47
    Activations Density 0.000%

    No Known Activations