© 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. 110634
    Prev
    Next
    INDEX
    Explanations

    black colors and realize

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

    instructions or descriptions

    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
     antiguas
    0.52
     reseñas
    0.52
     sabiduría
    0.51
     ಸರ್ಕಾರದ
    0.51
     いや
    0.50
    <unused1090>
    0.49
     代
    0.49
     歩
    0.49
     ර
    0.48
     wła
    0.48
    POSITIVE LOGITS
     Football
    0.49
     Railroad
    0.48
     Scrolling
    0.46
     Astronomical
    0.46
    Football
    0.46
     Mountain
    0.45
    犁
    0.44
    *
    0.44
    িমা
    0.43
     Tattoo
    0.43
    Activations Density 0.000%

    No Known Activations