© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86651
    Prev
    Next
    INDEX
    Explanations

    uo followed by names or technical terms

    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
    颼
    -2.86
    зраст
    -2.86
     nadru
    -2.75
    OUTUBE
    -2.70
     "")
    -2.53
    wezig
    -2.44
    此时
    -2.41
    臜
    -2.41
    脔
    -2.39
     Which
    -2.36
    POSITIVE LOGITS
    {
    4.09
    '
    3.16
    *
    3.03
    "
    2.81
     '
    2.80
    (
    2.52
    _
    2.50
    <
    2.50
    uo
    2.44
    AT
    2.42
    Activations Density 0.009%

    No Known Activations