© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2986
    Prev
    Next
    INDEX
    Explanations

    code and explanation sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     racional
    1.32
     Lego
    1.25
     rhubarb
    1.19
    🈶
    1.19
     قلنا
    1.16
     Encyclopaedia
    1.15
     ഇനി
    1.15
     Leibnitz
    1.13
     abolish
    1.13
     arouse
    1.12
    POSITIVE LOGITS
    kung
    1.07
    {"
    1.00
    การ
    0.97
    ıldı
    0.89
    യാണ്
    0.88
     मोर्चा
    0.85
    ア
    0.84
     подготов
    0.82
    ครับ
    0.81
    anud
    0.81
    Activations Density 0.822%

    No Known Activations