© 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. 1590
    Prev
    Next
    INDEX
    Explanations

    U.S

    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
     pagamento
    1.03
    hiyan
    0.98
     polít
    0.97
    柢
    0.97
    unan
    0.95
    ewords
    0.93
    সংযোগ
    0.92
     velho
    0.92
     oub
    0.86
     ambayo
    0.86
    POSITIVE LOGITS
    Tc
    1.40
    Ket
    1.39
     فونبیٹ
    1.37
     chili
    1.34
     Ket
    1.34
    浏
    1.34
     Tons
    1.33
    png
    1.32
     Chir
    1.31
    Sole
    1.31
    Activations Density 0.163%

    No Known Activations