© 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. 2362
    Prev
    Next
    INDEX
    Explanations

    function signature and return descriptions

    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
     karty
    1.13
    맵
    1.12
    Belarus
    1.09
     zemlje
    1.07
     compartido
    1.05
     voisin
    1.02
     Rusland
    1.01
    Rus
    1.00
    翌
    0.95
     eigens
    0.95
    POSITIVE LOGITS
    retching
    1.18
    ikl
    1.09
    ̮
    1.07
    ْ
    1.04
    eud
    1.03
    omicide
    1.00
    喇
    1.00
     transmembrane
    1.00
    ｷ
    0.99
    issner
    0.99
    Activations Density 0.089%

    No Known Activations