© 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. 59944
    Prev
    Next
    INDEX
    Explanations

    loud exclamations and criticism

    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
     not
    -1.77
    ↵
    -1.54
    ↵↵↵
    -1.50
     would
    -1.47
     today
    -1.40
     now
    -1.34
     get
    -1.31
     currently
    -1.30
    ’
    -1.30
     here
    -1.27
    POSITIVE LOGITS
     boya
    1.61
     ainfi
    1.51
     eene
    1.45
    isierten
    1.44
     ſeveral
    1.42
     juf
    1.41
     eier
    1.40
    ﹶ
    1.39
     otel
    1.39
     Monfieur
    1.38
    Activations Density 0.041%

    No Known Activations