© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5566
    Prev
    Next
    INDEX
    Explanations

    actions or suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    腕時計
    1.28
    👙
    1.15
     ży
    1.12
    💍
    1.12
    ETARY
    1.07
    📛
    1.05
     JANUARY
    1.05
    🎊
    1.04
    👰
    1.03
    🎎
    1.02
    POSITIVE LOGITS
     Anglia
    1.39
    ridor
    1.36
     Gambit
    1.35
    Colleg
    1.31
    示意
    1.30
     comparison
    1.29
    чева
    1.28
    textFile
    1.28
    Spectrum
    1.28
    半分
    1.27
    Activations Density 0.038%

    No Known Activations