© 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. 19911
    Prev
    Next
    INDEX
    Explanations

    ENV setting

    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
    Ꮉ
    -4.09
    屨
    -2.83
    珢
    -2.77
    </em>
    -2.73
    棪
    -2.66
    鹇
    -2.63
    wiſe
    -2.61
     ECONOMICS
    -2.44
    </sup>
    -2.44
     characterize
    -2.42
    POSITIVE LOGITS
     waning
    2.69
     According
    2.61
     '
    2.52
    \
    2.50
     
    2.47
     whats
    2.41
     s
    2.38
     saludables
    2.36
     After
    2.34
    葙
    2.34
    Activations Density 0.007%

    No Known Activations