© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3949
    Prev
    Next
    INDEX
    Explanations

    "i understand" or "i am"

    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
     nám
    1.17
    akova
    1.07
    uvos
    1.04
    kong
    1.02
    我要
    1.00
    ;</
    1.00
    sini
    0.98
     Bibliothek
    0.96
    atel
    0.95
    owska
    0.95
    POSITIVE LOGITS
     absolue
    1.39
    ISM
    1.17
     entirety
    1.15
    逢
    1.14
    圧力
    1.12
     gasped
    1.10
    TMS
    1.09
    ISON
    1.08
     desesper
    1.06
    ism
    1.06
    Activations Density 0.097%

    No Known Activations