© 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. 48273
    Prev
    Next
    INDEX
    Explanations

    Chen names and surnames

    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
    ’
    -3.39
    ll
    -2.94
     '
    -2.80
     ''
    -2.72
    nitř
    -2.69
    chen
    -2.67
     dizzy
    -2.55
     sowohl
    -2.52
    ?”
    -2.48
    鬟
    -2.30
    POSITIVE LOGITS
    屃
    2.69
    琑
    2.47
     If
    2.39
    嚳
    2.25
    bandcamp
    2.22
     Bemerkungen
    2.19
    餍
    2.16
    ↑↑↑</
    2.14
     município
    2.14
     vostri
    2.13
    Activations Density 0.005%

    No Known Activations