© 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. 10-GEMMASCOPE-RES-131K
    7. 10211
    Prev
    Next
    INDEX
    Explanations

    main form/mechanism/cause/component

    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
     minimale
    -1.69
     cúp
    -1.67
     marbre
    -1.64
     aficionados
    -1.63
    ܇
    -1.61
     superstars
    -1.57
     unſ
    -1.55
    dillos
    -1.55
     farine
    -1.54
     patate
    -1.54
    POSITIVE LOGITS
     in
    1.97
     way
    1.78
     not
    1.67
     why
    1.64
    </b>
    1.63
     first
    1.57
    <bos>
    1.55
     Our
    1.55
     '
    1.55
     of
    1.53
    Activations Density 0.065%

    No Known Activations