© 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. 6544
    Prev
    Next
    INDEX
    Explanations

    C code structures

    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
     removal
    0.97
    removal
    0.93
     ē
    0.89
    oderm
    0.86
    】.
    0.78
     waw
    0.75
     제거
    0.74
     cloro
    0.73
    )}^
    0.73
     entfernen
    0.73
    POSITIVE LOGITS
     Zeitung
    1.88
     Alger
    1.81
     Mexicana
    1.73
    知らない
    1.71
    人不
    1.70
    Begriffsklär
    1.68
     Kleine
    1.68
     Fahr
    1.67
     mapDispatch
    1.65
     Mink
    1.65
    Activations Density 0.002%

    No Known Activations