© 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. 2431
    Prev
    Next
    INDEX
    Explanations

    using commands or tools

    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
    requencies
    0.76
    rizes
    0.75
    %'
    0.73
    toml
    0.71
    ilas
    0.69
    advant
    0.68
    %"
    0.68
    getKeys
    0.67
    arrant
    0.67
    ohms
    0.66
    POSITIVE LOGITS
     продъл
    1.50
     CLOS
    1.49
    走了
    1.45
    焯
    1.45
    跪
    1.43
    进
    1.40
     placer
    1.36
    ัก
    1.35
     cáo
    1.34
    routeProvider
    1.33
    Activations Density 0.153%

    No Known Activations