© 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. 13051
    Prev
    Next
    INDEX
    Explanations

    language, numbers, and symbols

    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
    ++++
    0.43
     Graves
    0.40
    proguard
    0.40
     linewidth
    0.40
    actionBarTab
    0.40
     tetanus
    0.39
     sharpness
    0.38
    setLookAndFeel
    0.38
     गंभीर
    0.38
     contagious
    0.38
    POSITIVE LOGITS
     जरुरी
    0.41
    \
    0.40
    Projection
    0.38
    认识
    0.38
    zione
    0.38
    %。
    0.38
    sects
    0.38
    上述
    0.37
    Coal
    0.37
     personnaliser
    0.37
    Activations Density 0.000%

    No Known Activations