© 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. 150955
    Prev
    Next
    INDEX
    Explanations

    drinking Red Bull

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

    eggs, research, experience

    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
     diffé
    0.41
    ยายน
    0.38
    鰍
    0.38
     Directorate
    0.38
     Kval
    0.38
     различи
    0.38
     ब्राह्मण
    0.37
    ㄩ
    0.37
     Wharf
    0.37
     admissibility
    0.37
    POSITIVE LOGITS
    dude
    0.48
     for
    0.46
    NW
    0.46
     logra
    0.46
    numbers
    0.45
     loke
    0.45
     sólida
    0.44
    SleepHours
    0.44
    ሎችን
    0.44
     izinsuku
    0.43
    Activations Density 0.000%

    No Known Activations