© 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. 74933
    Prev
    Next
    INDEX
    Explanations

    Israel

    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
    ’
    -2.73
    就像是
    -2.48
    就不能
    -2.44
     wayward
    -2.34
     сеть
    -2.34
     payé
    -2.33
     unsuitable
    -2.31
    /
    -2.30
     «
    -2.28
     nasze
    -2.28
    POSITIVE LOGITS
    枼
    3.25
    鉺
    3.11
     engl
    2.78
    栳
    2.75
     riga
    2.66
     klaus
    2.63
     kamb
    2.61
     mika
    2.61
     siena
    2.59
     meis
    2.52
    Activations Density 0.006%

    No Known Activations