© 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. 130814
    Prev
    Next
    INDEX
    Explanations

    symbols 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
     to
    -2.13
     
    -2.00
     The
    -1.90
     in
    -1.86
    er
    -1.79
    ie
    -1.73
    ↵
    -1.69
     on
    -1.66
     is
    -1.63
    *
    -1.63
    POSITIVE LOGITS
     گرف
    2.09
     cará
    1.88
     diki
    1.84
     bluz
    1.82
    文學
    1.80
     lentejuelas
    1.77
    Răspunde
    1.74
    嫘
    1.71
    Poznám
    1.70
     tabak
    1.70
    Activations Density 0.002%

    No Known Activations