© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5030
    Prev
    Next
    INDEX
    Explanations

    movement and sensory actions

    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
    lvl
    1.50
    enance
    1.37
    ustic
    1.36
    ransfer
    1.36
    兑
    1.35
     Converter
    1.33
    ehle
    1.33
    xxx
    1.31
    eser
    1.28
    uil
    1.27
    POSITIVE LOGITS
    minute
    1.33
     Brodie
    1.23
    Minute
    1.18
     minute
    1.16
    мина
    1.13
    Riley
    1.12
    мини
    1.12
    Removed
    1.11
    [(\
    1.11
    nbhd
    1.08
    Activations Density 0.021%

    No Known Activations