© 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. 10603
    Prev
    Next
    INDEX
    Explanations

    URLs, technical terms, discount, resource

    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
     시스템
    1.34
    marshalN
    1.27
    시스템
    1.25
     Optionen
    1.19
     Система
    1.17
    㑼
    1.17
    ávat
    1.17
    StatusCodes
    1.17
    缺
    1.15
     stratification
    1.15
    POSITIVE LOGITS
    lovers
    1.08
     dang
    0.97
     famous
    0.95
     merr
    0.95
     ridiculously
    0.94
     famously
    0.93
     pound
    0.93
     Cream
    0.93
    lover
    0.92
    so
    0.92
    Activations Density 0.130%

    No Known Activations