© 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. 220166
    Prev
    Next
    INDEX
    Explanations

    Oprah Winfrey

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

    safe and respectful topics

    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
     gambling
    0.43
     baseball
    0.43
     لكرة
    0.43
     football
    0.42
    /-}$
    0.41
     drives
    0.41
    football
    0.41
    time
    0.40
    øn
    0.39
     Matemática
    0.39
    POSITIVE LOGITS
     OPCODE
    0.51
    ITECTURE
    0.49
     เกี่ยว
    0.49
    yfikacji
    0.48
    zonego
    0.48
     Giuliani
    0.47
    RESSION
    0.47
    IGATION
    0.47
     ና
    0.46
     Спа
    0.46
    Activations Density 0.001%

    No Known Activations