© 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. 22-GEMMASCOPE-RES-131K
    7. 39540
    Prev
    Next
    INDEX
    Explanations

    industry news and events

    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_22/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
     because
    -1.88
     people
    -1.76
     children
    -1.69
     family
    -1.59
     using
    -1.37
     school
    -1.35
     Because
    -1.33
     one
    -1.30
     without
    -1.30
    because
    -1.26
    POSITIVE LOGITS
     industry
    1.61
    industry
    1.49
    וּ
    1.46
     analysts
    1.45
     السوق
    1.44
     analyst
    1.36
     impecable
    1.31
    靭
    1.30
     Cedex
    1.27
     düğün
    1.26
    Activations Density 0.090%

    No Known Activations