© 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. 225000
    Prev
    Next
    INDEX
    Explanations

    definitions and classifications

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

    by expectations or assumptions

    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
     rá
    0.49
     divulgação
    0.48
     найд
    0.48
    मियल
    0.47
     hér
    0.47
     Reine
    0.47
     liberar
    0.47
    誘
    0.47
     riddled
    0.46
     Rodríguez
    0.46
    POSITIVE LOGITS
    运动员
    0.47
    ATH
    0.44
     AUTHORS
    0.44
    sports
    0.41
     функциона
    0.40
    >=</
    0.39
    tech
    0.39
    却是
    0.39
    дер
    0.39
    squares
    0.39
    Activations Density 0.000%

    No Known Activations