© 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. 37741
    Prev
    Next
    INDEX
    Explanations

    URLs with docs

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

    documentation links

    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
    idespread
    0.44
    ULTURAL
    0.43
     ACTIVITIES
    0.41
    Corollary
    0.41
    URAL
    0.41
    কারীদের
    0.39
    兘
    0.38
    ನ್ನ
    0.37
     annular
    0.37
     glLight
    0.37
    POSITIVE LOGITS
     ваш
    0.48
     éventuellement
    0.47
     geliştir
    0.46
     réglementation
    0.46
    cipe
    0.46
    عليه
    0.45
    ز
    0.45
    itemName
    0.45
     klas
    0.44
     buil
    0.44
    Activations Density 0.000%

    No Known Activations