© 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. 5954
    Prev
    Next
    INDEX
    Explanations

    python `__init__` and `__main__`

    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
     potreb
    2.01
     紅
    1.90
    向
    1.89
     будем
    1.89
    nextDouble
    1.87
    ສຸດ
    1.82
     :"
    1.82
     населения
    1.81
    เรา
    1.81
     citiz
    1.80
    POSITIVE LOGITS
    __,
    2.29
    __.
    2.10
    __
    2.07
    __).
    2.06
    __:
    2.05
    __)
    1.92
    __'
    1.92
    __()
    1.84
    __':
    1.83
    __/
    1.75
    Activations Density 0.002%

    No Known Activations