© 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. 21041
    Prev
    Next
    INDEX
    Explanations

    langdurige, state for, to request

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

    stats and technical information

    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
    inin
    0.47
    တတ်
    0.47
    ಲೆ
    0.42
    plated
    0.41
     드라마
    0.41
    }&
    0.40
     মতো
    0.39
     powied
    0.39
     movers
    0.39
    ‘
    0.39
    POSITIVE LOGITS
    BeforeText
    0.48
     ז
    0.46
     появился
    0.46
    ُوا
    0.46
     выйти
    0.46
     единственный
    0.46
     auftreten
    0.45
     инду
    0.44
     особы
    0.44
    วิทยา
    0.44
    Activations Density 0.000%

    No Known Activations