© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11021
    Prev
    Next
    INDEX
    Explanations

    daily eating and organizing

    np_acts-logits-general · gemini-2.5-flash-lite

    card related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
     arrive
    0.54
    宿泊
    0.51
     arrived
    0.50
     parking
    0.50
     brunch
    0.50
    arrive
    0.49
     arrives
    0.48
    🍮
    0.45
    Parking
    0.45
    parking
    0.44
    POSITIVE LOGITS
    每天
    0.60
     daily
    0.52
    每日
    0.51
     ежедневно
    0.50
     diariamente
    0.50
    utiliser
    0.49
    daily
    0.48
    毎日
    0.48
    几次
    0.47
     vyu
    0.46
    Activations Density 0.099%

    No Known Activations