© 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. 17909
    Prev
    Next
    INDEX
    Explanations

    units and measurements

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

    converts, impedance, per hour, Hertz, Q, I

    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
    民众
    0.48
     让
    0.46
     değişken
    0.46
    众人
    0.46
    队员
    0.46
     ይሆ
    0.45
    谲
    0.45
    游戏中
    0.43
    愺
    0.42
     khiến
    0.42
    POSITIVE LOGITS
     normalized
    0.52
     normalised
    0.47
     extrapolated
    0.47
     peak
    0.46
     log
    0.44
     per
    0.43
    總
    0.43
     equivalent
    0.43
    normalized
    0.43
     measured
    0.42
    Activations Density 0.049%

    No Known Activations