© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113316
    Prev
    Next
    INDEX
    Explanations

    words starting with Uni

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     worin
    -2.84
    臵
    -2.80
    菒
    -2.73
    <bos>
    -2.70
     baden
    -2.66
    葙
    -2.66
     heilig
    -2.64
     แต่
    -2.61
    乆
    -2.61
    かっこいい
    -2.58
    POSITIVE LOGITS
    (
    3.03
     believes
    2.84
     seems
    2.83
     finds
    2.80
    //
    2.77
    [
    2.73
     combines
    2.69
     thinks
    2.69
     encompasses
    2.66
    ⎆
    2.63
    Activations Density 0.005%

    No Known Activations