© 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. 9766
    Prev
    Next
    INDEX
    Explanations

    Kō 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
    lossians
    -3.02
    髅
    -2.69
    龊
    -2.66
    .
    -2.58
    ↵↵
    -2.41
    鸯
    -2.39
    ဴ
    -2.25
    ścioła
    -2.22
    ⭏
    -2.19
    ’，
    -2.17
    POSITIVE LOGITS
    9
    2.94
    ‐
    2.80
    {
    2.59
    }$
    2.52
    8
    2.52
    0
    2.41
    7
    2.36
    ่านั้น
    2.33
    3
    2.33
    盉
    2.31
    Activations Density 0.003%

    No Known Activations