© 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. 3205
    Prev
    Next
    INDEX
    Explanations

    not suitable or able

    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
    営業時間
    1.49
    WI
    1.40
     Osw
    1.40
    doch
    1.39
    świę
    1.36
    깁
    1.34
    wara
    1.34
    カロ
    1.32
    prote
    1.32
     mero
    1.30
    POSITIVE LOGITS
    ющи
    1.01
    ية
    0.97
     that
    0.94
    дца
    0.91
    攪
    0.91
    ье
    0.90
    でしょう
    0.90
    lais
    0.90
    ais
    0.89
    CommonAncestor
    0.89
    Activations Density 0.116%

    No Known Activations