© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10853
    Prev
    Next
    INDEX
    Explanations

    сложной

    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
    Not in Any Lists

    No Comments

    Negative Logits
    श्किल
    2.15
    olecules
    2.15
    zego
    2.14
    ྜ
    2.14
    ducting
    2.13
     pełni
    2.11
    scriptstyle
    2.10
    *\
    2.08
    ক্তিক
    2.07
    tela
    2.06
    POSITIVE LOGITS
    woman
    2.64
    AppDesigner
    2.38
    ор
    2.29
    imony
    2.27
    ione
    2.18
    ി
    2.16
     Thực
    2.16
     opp
    2.15
    لسل
    2.14
    ዶ
    2.13
    Activations Density 0.003%

    No Known Activations