© 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. 6457
    Prev
    Next
    INDEX
    Explanations

    data processing and analysis

    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
    吒
    1.80
    elsior
    1.76
    outed
    1.66
    urek
    1.62
    uws
    1.59
    endium
    1.57
    odies
    1.54
    ored
    1.54
    ="//
    1.53
    zeit
    1.52
    POSITIVE LOGITS
    กล
    1.45
    estima
    1.43
     信
    1.35
    rón
    1.35
     tappa
    1.32
     assi
    1.32
    ゲスト
    1.31
     Algonquin
    1.30
     conve
    1.30
     verr
    1.29
    Activations Density 0.020%

    No Known Activations