© 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. 27025
    Prev
    Next
    INDEX
    Explanations

    whimsical kitchen

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

    commands and code

    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
    م
    0.64
    b
    0.54
    ن
    0.54
    m
    0.51
    ম
    0.51
    新
    0.49
    T
    0.48
    Fellow
    0.48
     correção
    0.47
     Perfect
    0.46
    POSITIVE LOGITS
    ercus
    0.51
    ayd
    0.50
     //$
    0.49
    aarrggbb
    0.48
    زمانہ
    0.48
     gypsy
    0.48
    向前
    0.47
    ೨
    0.47
    व्यक्त
    0.46
    ्रू
    0.46
    Activations Density 0.000%

    No Known Activations