© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10807
    Prev
    Next
    INDEX
    Explanations

    CUDA __global__ keyword

    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_7_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
    𝚞
    1.83
    Liv
    1.82
    NGC
    1.79
    ﺅ
    1.79
    boo
    1.78
    𝚎
    1.78
    চ্ছিল
    1.78
    Nota
    1.73
    !`
    1.70
    𝚊
    1.68
    POSITIVE LOGITS
    s
    2.82
    ों
    2.71
    ের
    2.51
    ly
    2.44
    nya
    2.23
    了
    2.17
    თვის
    2.10
    ishops
    2.09
    nets
    2.08
    에
    2.05
    Activations Density 0.044%

    No Known Activations