© 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. 154193
    Prev
    Next
    INDEX
    Explanations

    how to choose

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

    different ways

    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
    '
    0.53
     Ame
    0.50
     Bulk
    0.47
    ເຮັດ
    0.46
    ></
    0.45
     الأم
    0.43
     CharPtr
    0.43
     Sarmiento
    0.43
     Campeonato
    0.43
    😂😂
    0.43
    POSITIVE LOGITS
    ucci
    0.48
    ಟ್ಟಿ
    0.48
    ichtet
    0.47
    етки
    0.46
    ichte
    0.46
    ്രി
    0.46
    डेड
    0.45
    ätte
    0.45
    ಿಸಿದೆ
    0.44
    ichten
    0.44
    Activations Density 0.000%

    No Known Activations