© 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. 8147
    Prev
    Next
    INDEX
    Explanations

    stop execution

    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
    斯
    0.38
    icama
    0.34
     사람들이
    0.32
     تهیه
    0.31
     Stephen
    0.30
    အရေ
    0.29
     Shetland
    0.29
    玄
    0.29
     Russell
    0.29
     তাপমাত্রা
    0.29
    POSITIVE LOGITS
     dienen
    0.37
     interrupting
    0.37
     imedi
    0.37
    पे
    0.35
     inmedi
    0.34
     inmediato
    0.33
     delay
    0.33
     imediat
    0.33
     inmediata
    0.33
     execute
    0.32
    Activations Density 0.098%

    No Known Activations