© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9751
    Prev
    Next
    INDEX
    Explanations

    optim

    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
     时尚
    1.66
     餐
    1.53
     laminate
    1.48
     스타일
    1.44
     项
    1.42
     红
    1.39
     쇼
    1.38
     茶
    1.34
     设计
    1.33
     标准
    1.30
    POSITIVE LOGITS
    nings
    1.27
    g
    1.24
    inas
    1.23
    ning
    1.23
    rer
    1.22
    ou
    1.22
    izações
    1.22
    é
    1.21
    jit
    1.21
    scaler
    1.20
    Activations Density 0.000%

    No Known Activations