© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5187
    Prev
    Next
    INDEX
    Explanations

    destination assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    =\"
    1.93
    ERCIAL
    1.89
     resembles
    1.80
     simulates
    1.80
    젯
    1.79
    ̡
    1.76
     NONINFRINGEMENT
    1.76
    olí
    1.76
     gamblers
    1.75
    RICAL
    1.75
    POSITIVE LOGITS
    addAll
    1.64
     пояс
    1.64
     ил
    1.59
     все
    1.57
     по
    1.49
    进一步
    1.49
     в
    1.49
     درآمد
    1.49
    В
    1.48
    庭
    1.47
    Activations Density 0.015%

    No Known Activations