© 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. 28370
    Prev
    Next
    INDEX
    Explanations

    increase and related metrics

    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
    ajaan
    -1.02
    完全
    -0.96
    ادامه
    -0.95
     Preis
    -0.94
     تھے
    -0.93
    However
    -0.92
    その他
    -0.90
     typelib
    -0.88
    撃
    -0.88
    フィ
    -0.86
    POSITIVE LOGITS
     by
    1.33
    endimiento
    1.29
     in
    1.27
     volume
    1.07
     coefficient
    1.01
     than
    1.00
     chances
    1.00
     increase
    0.98
     number
    0.98
    乐趣
    0.95
    Activations Density 0.129%

    No Known Activations