© 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. 11199
    Prev
    Next
    INDEX
    Explanations

    roughly chronological or ranked order

    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
    ilt
    0.43
     ያስፈል
    0.40
    ౖ
    0.40
    ωση
    0.40
     Dixit
    0.40
     프로
    0.39
    ibilities
    0.39
     leaderboard
    0.38
    <unused19>
    0.38
    Har
    0.38
    POSITIVE LOGITS
     months
    0.44
     según
    0.41
     después
    0.41
     वेलकम
    0.39
    months
    0.39
    等你
    0.38
     shortly
    0.37
     três
    0.36
     Three
    0.36
     üç
    0.35
    Activations Density 0.003%

    No Known Activations