© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11868
    Prev
    Next
    INDEX
    Explanations

    progressive physical improvement

    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
    ớp
    1.83
    UnderWater
    1.69
    鏄
    1.57
    lenie
    1.55
    人民币
    1.55
     reméd
    1.52
    льное
    1.49
    ulloch
    1.48
    lije
    1.47
    ピッ
    1.47
    POSITIVE LOGITS
     벗
    1.06
     الطرف
    1.05
    GA
    1.01
    TO
    1.00
    낸
    0.96
     士
    0.95
    죽
    0.95
     martyr
    0.94
    헌
    0.94
     DE
    0.94
    Activations Density 0.256%

    No Known Activations