© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10208
    Prev
    Next
    INDEX
    Explanations

    describing ways to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    м
    3.27
    দিষ্ট
    2.86
    ணற
    2.72
    нской
    2.66
    antd
    2.63
     setIsLoading
    2.62
     Aztecs
    2.57
    깐
    2.57
    絆
    2.57
    ButtonGroup
    2.54
    POSITIVE LOGITS
    t
    3.53
    sen
    3.43
    ds
    3.25
    tic
    3.17
    sy
    3.12
    tica
    3.10
    tas
    2.92
    tom
    2.91
    tap
    2.85
    ت
    2.77
    Activations Density 0.015%

    No Known Activations