© 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. 22-GEMMASCOPE-RES-131K
    7. 84230
    Prev
    Next
    INDEX
    Explanations

    Indian names 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_22/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
    the
    -1.82
    更何况
    -1.75
     of
    -1.73
    p
    -1.66
    紧接着
    -1.62
    就连
    -1.57
    なので
    -1.55
    <bos>
    -1.48
    for
    -1.47
    fi
    -1.46
    POSITIVE LOGITS
     Vergnügen
    2.00
     Fazit
    1.84
     antiguas
    1.79
    Odpovědět
    1.77
     lusso
    1.73
     campañas
    1.71
     lámparas
    1.71
     comiendo
    1.70
     Gefühl
    1.68
     sorpresas
    1.68
    Activations Density 0.001%

    No Known Activations