© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1147
    Prev
    Next
    INDEX
    Explanations

    questions about color

    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
     (
    1.88
    1.87
     "(
    1.72
     ten
    1.68
    .
    1.67
     March
    1.67
    ).
    1.62
     з
    1.62
    ↵↵
    1.60
     July
    1.60
    POSITIVE LOGITS
    łączy
    2.24
     outils
    2.20
     outil
    2.18
     lingkungan
    2.16
    getPopulation
    2.16
    ulièrement
    2.12
     això
    2.08
     উন্নয়নে
    2.07
     équipements
    2.07
    histoire
    2.06
    Activations Density 0.099%

    No Known Activations