© 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. 2814
    Prev
    Next
    INDEX
    Explanations

    timing, seconds, milliseconds, latency

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

    timing and latency

    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
     дому
    0.52
     хора
    0.51
    罵
    0.49
    юза
    0.49
     навчання
    0.49
    テナンス
    0.48
    鹸
    0.48
     социа
    0.47
    斛
    0.47
    瘡
    0.47
    POSITIVE LOGITS
     milliseconds
    1.41
     seconds
    1.27
     microseconds
    1.23
     Sekunden
    1.09
    seconds
    1.06
    milliseconds
    1.06
     Seconds
    1.03
     timing
    1.01
     segundos
    1.01
     latency
    0.99
    Activations Density 0.092%

    No Known Activations