© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6680
    Prev
    Next
    INDEX
    Explanations

    options for communication style

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Chr
    1.06
     tá
    1.04
     CHRIST
    1.04
     SUNY
    1.02
     palest
    0.99
     curr
    0.99
     critérios
    0.97
    ษ
    0.97
     arg
    0.96
     trú
    0.96
    POSITIVE LOGITS
    ebook
    1.30
    hao
    1.17
    uyor
    1.07
    هم
    1.07
    pageNum
    1.07
    <unused973>
    1.05
    <unused1644>
    1.04
    /).
    1.03
    <unused1008>
    1.03
    ousands
    1.02
    Activations Density 0.008%

    No Known Activations