© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163247
    Prev
    Next
    INDEX
    Explanations

    car securely, now that, exclusive perspective

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

    list prefixes and choices

    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
     Computational
    0.54
     컴퓨
    0.53
     Gaston
    0.47
     꿈
    0.47
     World
    0.47
     Rasul
    0.46
    itiba
    0.46
     Dreaming
    0.46
     y
    0.45
     Taj
    0.45
    POSITIVE LOGITS
    Ris
    0.47
    SRPS
    0.47
    の手
    0.43
     linkages
    0.43
     abiertas
    0.43
     automatis
    0.43
    Remain
    0.42
    ABL
    0.42
    ONTO
    0.42
    /');
    0.41
    Activations Density 0.001%

    No Known Activations