© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9583
    Prev
    Next
    INDEX
    Explanations

    unexpectedly or mysteriously

    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
    шёл
    -1.30
     когато
    -1.29
     dévou
    -1.28
     vétérina
    -1.27
    และ
    -1.27
    
    -1.27
    咔
    -1.26
    Initially
    -1.24
    — 
    -1.24
    最近の
    -1.23
    POSITIVE LOGITS
     or
    1.92
     out
    1.68
     more
    1.63
     everything
    1.55
     this
    1.50
     provide
    1.49
     already
    1.41
     whose
    1.41
     only
    1.40
     up
    1.38
    Activations Density 0.087%

    No Known Activations