© 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. 104065
    Prev
    Next
    INDEX
    Explanations

    technical and foreign words

    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
    ៚
    -2.44
     availa
    -2.44
    身为
    -2.39
    A
    -2.34
    genodigd
    -2.33
    peut
    -2.30
    these
    -2.28
     amortecedor
    -2.28
    ところで
    -2.27
    Bringing
    -2.27
    POSITIVE LOGITS
     It
    2.77
     This
    2.52
    “
    2.48
    鷓
    2.30
     Diese
    2.25
     Dieses
    2.25
     Whether
    2.23
    izes
    2.13
    नलोड
    2.09
     That
    2.08
    Activations Density 0.000%

    No Known Activations