© 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. 74924
    Prev
    Next
    INDEX
    Explanations

    specific names and people

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

    boys tremble

    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
     змін
    0.58
     البته
    0.49
     tehát
    0.49
     inertial
    0.48
     indexOf
    0.48
     clonal
    0.48
     숫자
    0.47
     ;-)
    0.46
     WHEN
    0.46
    variable
    0.46
    POSITIVE LOGITS
     rumored
    0.49
    ano
    0.49
    omo
    0.47
    Girl
    0.47
    িন্দ
    0.47
    BO
    0.46
    ino
    0.46
    oni
    0.46
    itter
    0.45
    Bo
    0.45
    Activations Density 0.001%

    No Known Activations