© 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-65K
    7. 46050
    Prev
    Next
    INDEX
    Explanations

    conversions and calculations

    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_65k_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
     USING
    0.50
    𝗺
    0.43
    ྞ
    0.41
     Dien
    0.39
     Relevance
    0.39
     மற்றொரு
    0.39
     alcohols
    0.38
    chus
    0.38
    𝗱
    0.38
    ски
    0.38
    POSITIVE LOGITS
    老的
    0.38
    úrate
    0.37
    تم
    0.37
    ల్లి
    0.36
     damals
    0.36
    了一声
    0.36
    plural
    0.36
    نم
    0.35
    当时
    0.35
    تمي
    0.35
    Activations Density 0.007%

    No Known Activations