© 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. 149231
    Prev
    Next
    INDEX
    Explanations

    prediction and numbers

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

    action verbs for processes

    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
     Huge
    0.46
     komunitas
    0.45
    OfInterest
    0.45
     ね
    0.41
     माध्यमातून
    0.41
     магазина
    0.41
     культуры
    0.40
     народа
    0.40
     людей
    0.40
     trillion
    0.40
    POSITIVE LOGITS
    Лі
    0.40
     assessment
    0.40
    letzt
    0.40
    Чи
    0.39
     svaki
    0.39
     (#
    0.39
     Sevilla
    0.38
     (“
    0.38
    꺄
    0.38
    leveland
    0.38
    Activations Density 0.002%

    No Known Activations