© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1601
    Prev
    Next
    INDEX
    Explanations

    colors and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     dyes
    1.01
    Others
    0.97
     lainnya
    0.90
     Others
    0.89
     ALLOYS
    0.83
     échantillons
    0.82
    oxins
    0.82
     색
    0.80
     muque
    0.79
    colours
    0.79
    POSITIVE LOGITS
     either
    1.36
    either
    1.15
     mostly
    0.97
     two
    0.96
     mainly
    0.95
     both
    0.95
     primarily
    0.93
     what
    0.90
     predominantly
    0.89
     solely
    0.89
    Activations Density 0.403%

    No Known Activations