© 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. 3293
    Prev
    Next
    INDEX
    Explanations

    artistic styles and movements

    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
    erver
    2.99
    みが
    2.85
    унд
    2.83
    彝
    2.77
    ﻟ
    2.72
    undas
    2.70
    മിഷ
    2.68
    byshev
    2.63
    啪
    2.63
    undum
    2.57
    POSITIVE LOGITS
    tobs
    2.89
    ifice
    2.54
    heastern
    2.51
    ंख
    2.49
    সম্মত
    2.42
    िकल्स
    2.38
    scenes
    2.35
    カイブ
    2.35
    lo
    2.35
    angement
    2.31
    Activations Density 0.135%

    No Known Activations