© 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-16K
    7. 296
    Prev
    Next
    INDEX
    Explanations

    analysis and exploration

    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_16k_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
     ONLY
    0.33
    0.32
     actually
    0.29
     eats
    0.29
     չ
    0.29
     blob
    0.29
    لوار
    0.29
     trivially
    0.29
     بۇ
    0.28
     vendu
    0.28
    POSITIVE LOGITS
    探讨
    0.33
     способствует
    0.32
     обеспечивает
    0.30
    у
    0.29
    有助于
    0.29
     Provides
    0.28
    Provides
    0.28
     exploring
    0.28
    ifting
    0.28
     insightful
    0.28
    Activations Density 3.094%

    No Known Activations