© 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. 87166
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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
    *
    -3.34
    \
    -2.66
    -2.50
     Our
    -2.47
    ↵↵
    -2.45
    .
    -2.36
     
    -2.34
     comenzar
    -2.34
     contribuer
    -2.33
     You
    -2.30
    POSITIVE LOGITS
    咵
    3.30
    鋦
    3.17
    ྵ
    3.08
    ዣ
    3.05
     стоковая
    3.05
    鰨
    2.97
    งิน
    2.97
    Ꭳ
    2.95
    鯷
    2.95
    蛧
    2.92
    Activations Density 0.001%
    No Known Activations