© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19292
    Prev
    Next
    INDEX
    Explanations

    following punctuation or 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
     Jerome
    0.45
    établissement
    0.43
    觚
    0.43
     Footage
    0.41
     Waterfront
    0.41
    Frederick
    0.41
    utc
    0.40
    ADT
    0.40
     Jerry
    0.39
    Woods
    0.38
    POSITIVE LOGITS
     mysteriously
    0.42
     perceptible
    0.42
     intuitively
    0.39
     intégré
    0.38
     대신
    0.38
     आरोग्य
    0.38
     ї
    0.37
     biến
    0.37
     לו
    0.37
     instinctively
    0.37
    Activations Density 0.000%

    No Known Activations