© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43004
    Prev
    Next
    INDEX
    Explanations

    dates and availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.54
    皆
    0.46
     yield
    0.45
    to
    0.45
     concession
    0.44
     successfully
    0.43
     ticketing
    0.42
     ballerina
    0.42
    ifying
    0.41
    ;
    0.41
    POSITIVE LOGITS
     মুহুর
    0.44
    ್ಟ
    0.44
    िज्या
    0.44
    ствии
    0.43
    ۆی
    0.43
    ಂಭ
    0.42
     часть
    0.41
    PARTMENT
    0.41
    питы
    0.41
     части
    0.40
    Activations Density 0.006%

    No Known Activations