© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8254
    Prev
    Next
    INDEX
    Explanations

    eye, RAM, eligible, odd

    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
    о
    0.31
     the
    0.29
    у
    0.29
    the
    0.29
    а
    0.28
    е
    0.28
    и
    0.27
    D
    0.26
     remarkably
    0.25
    S
    0.25
    POSITIVE LOGITS
     protéines
    0.28
     séparation
    0.28
    AutoStabilise
    0.28
    权重
    0.26
    UnderWater
    0.26
    gäng
    0.26
    gdock
    0.25
     diarrh
    0.25
     épaules
    0.25
    gä
    0.25
    Activations Density 0.303%

    No Known Activations