© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2724
    Prev
    Next
    INDEX
    Explanations

    AI, Amazon, `curl`, Bus, Vercel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     个
    1.74
     那麼
    1.73
     修
    1.72
     的
    1.69
     많이
    1.62
     但是
    1.58
     健康
    1.58
     小
    1.58
     배
    1.57
    딧
    1.57
    POSITIVE LOGITS
     contexte
    2.31
     tentativa
    1.76
     Kapol
    1.68
     Governo
    1.64
     inéd
    1.59
     declarado
    1.58
     incumbent
    1.58
     denuncia
    1.56
     desperation
    1.56
     उन्‍ह
    1.56
    Activations Density 0.257%

    No Known Activations