© 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. 224101
    Prev
    Next
    INDEX
    Explanations

    charge to Odyssey

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

    freedom, lying, dragging, Box, attacks

    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
    鲛
    0.54
    ματο
    0.48
    ᒐ
    0.46
    沃尔
    0.46
    晫
    0.45
    CLOSE
    0.45
    -'
    0.45
    തമായ
    0.45
    зма
    0.45
    ว์
    0.44
    POSITIVE LOGITS
     som
    0.48
    ul
    0.48
     f
    0.46
      
    0.46
    uska
    0.46
     li
    0.46
     paci
    0.45
     per
    0.45
     cultures
    0.45
    utive
    0.44
    Activations Density 0.000%

    No Known Activations