© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 87147
    Prev
    Next
    INDEX
    Explanations

    geometry involving circles

    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
     ۱۷
    -1.78
    車を
    -1.62
     ۱۱
    -1.59
     they
    -1.59
     ۱۵
    -1.53
    捱
    -1.51
     interess
    -1.50
    rite
    -1.49
    ne
    -1.49
    ed
    -1.48
    POSITIVE LOGITS
     newly
    1.62
     only
    1.59
    uniqlo
    1.57
    Pgina
    1.48
     seleccionadas
    1.46
    wnętr
    1.45
     estrictamente
    1.45
     語
    1.43
    butuhkan
    1.43
    jadikan
    1.42
    Activations Density 0.023%

    No Known Activations