© 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. 58683
    Prev
    Next
    INDEX
    Explanations

    three

    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
     Kedua
    -1.19
     eighty
    -1.15
    \'{
    -1.14
     Jenderal
    -1.11
     twenty
    -1.09
     منذ
    -1.09
     \"
    -1.08
     Darío
    -1.06
     kedua
    -1.06
     ninety
    -1.05
    POSITIVE LOGITS
    three
    1.92
     trio
    1.78
     trois
    1.70
     तीन
    1.70
     three
    1.67
     трех
    1.57
     drei
    1.46
    三个
    1.43
     trzech
    1.40
     Three
    1.38
    Activations Density 0.125%

    No Known Activations