© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12784
    Prev
    Next
    INDEX
    Explanations

    keywords like func, type, struct

    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_13_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
     épais
    1.35
     zéro
    1.19
    俯
    1.18
    ⸜
    1.17
    噜
    1.15
    χυ
    1.14
    лін
    1.11
    uların
    1.10
    ✷
    1.08
     variés
    1.08
    POSITIVE LOGITS
    nt
    1.36
    loc
    1.21
    doc
    1.14
     داشته
    1.14
     ocur
    1.13
    biological
    1.13
     Ell
    1.13
    ٖ
    1.12
     ঘটবে
    1.11
     Entom
    1.11
    Activations Density 0.002%

    No Known Activations