© 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. 24625
    Prev
    Next
    INDEX
    Explanations

    dataset structure

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

    installation and definitions

    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
     ಔ
    0.51
     tiež
    0.49
     גם
    0.46
     facilmente
    0.46
     температуре
    0.44
    ма
    0.44
     ი
    0.43
     deshalb
    0.43
    狠狠
    0.43
     інформа
    0.42
    POSITIVE LOGITS
    Setter
    0.47
     Development
    0.46
    Development
    0.42
     Plantation
    0.42
    🏔
    0.41
    CreateModel
    0.41
     and
    0.40
    物质
    0.39
    が通販できます
    0.39
     Foundation
    0.39
    Activations Density 0.000%

    No Known Activations