© 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. 10264
    Prev
    Next
    INDEX
    Explanations

    categorize them

    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
    ಖ್ಯ
    2.44
     ImageTk
    2.40
    뻔
    2.30
    컥
    2.29
     pygame
    2.29
    녘
    2.26
    ائج
    2.24
    чика
    2.18
    株
    2.14
    ف
    2.13
    POSITIVE LOGITS
    CM
    3.01
    Ca
    3.00
    үм
    2.99
    ́ch
    2.86
     sao
    2.85
    ́i
    2.80
    agory
    2.78
    JA
    2.77
     móc
    2.64
     Lowest
    2.64
    Activations Density 0.017%

    No Known Activations