© 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. 153622
    Prev
    Next
    INDEX
    Explanations

    clinical results and speed

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

    Chrome Extension

    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
    ل
    0.59
     FULL
    0.50
    স্
    0.49
     in
    0.48
     \
    0.48
     EMERGENCY
    0.47
    اص
    0.46
    emergency
    0.46
    ক
    0.46
    ပို
    0.46
    POSITIVE LOGITS
     уме
    0.48
     realização
    0.46
     visão
    0.46
     интерфей
    0.45
     изуча
    0.45
     проведение
    0.45
    ientes
    0.44
     стекло
    0.44
     функцию
    0.44
    водится
    0.44
    Activations Density 0.000%

    No Known Activations