© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5933
    Prev
    Next
    INDEX
    Explanations

    key terms and descriptors

    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
    假設
    1.02
     지금
    1.01
    叨
    0.98
    osaic
    0.96
    jecture
    0.95
    blings
    0.95
     很
    0.95
    碰到
    0.93
    дами
    0.93
     arrive
    0.91
    POSITIVE LOGITS
     Outstanding
    1.13
     Excellence
    1.11
     excelencia
    1.08
     categoria
    1.08
     kategori
    1.05
     chairmanship
    1.03
     décerné
    1.02
    奖
    1.02
    優秀
    1.02
     ausgezeichnet
    1.00
    Activations Density 0.328%

    No Known Activations