© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13445
    Prev
    Next
    INDEX
    Explanations

    Python function arguments and definitions

    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_13_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
     아직
    1.44
     Searching
    1.42
     블랙
    1.35
     單
    1.35
     نگاه
    1.33
     调用
    1.32
     黑
    1.32
     일단
    1.32
     是否
    1.32
     อยู่
    1.31
    POSITIVE LOGITS
     changé
    0.82
     changes
    0.80
     improvements
    0.79
    improvements
    0.77
    updater
    0.74
     clarifications
    0.74
     другое
    0.72
     autre
    0.70
    specific
    0.70
    これにより
    0.69
    Activations Density 0.009%

    No Known Activations