© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37875
    Prev
    Next
    INDEX
    Explanations

    show results

    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_34/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
    ambahkan
    -0.94
     квартиру
    -0.89
    Provide
    -0.77
    ได้
    -0.77
    änner
    -0.74
     Provide
    -0.74
    ibilidade
    -0.73
     Providing
    -0.73
    ismus
    -0.73
    interpre
    -0.72
    POSITIVE LOGITS
     show
    5.31
     showing
    5.22
     shows
    5.03
     showed
    4.50
    show
    4.19
    showing
    4.09
    Showing
    3.83
     Showing
    3.83
    shows
    3.78
     mostrar
    3.73
    Activations Density 0.254%

    No Known Activations