© 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. 204025
    Prev
    Next
    INDEX
    Explanations

    weekly honors

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

    rules and laws

    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
    ﺷ
    0.59
    ಿಕೆ
    0.59
    𝗱
    0.52
    дут
    0.52
    ಿಗ
    0.52
     이야기를
    0.49
    ‌ల
    0.49
    ŠE
    0.49
    𝒕
    0.49
     Elektrokhimiya
    0.48
    POSITIVE LOGITS
     -
    0.42
     Leclerc
    0.42
     Compaq
    0.41
    เกี่ยวกับ
    0.41
    US
    0.40
    Dock
    0.40
    Vectors
    0.40
    usher
    0.39
     Packers
    0.39
     mutex
    0.38
    Activations Density 0.001%

    No Known Activations