© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70984
    Prev
    Next
    INDEX
    Explanations

    program prefixes followed by suffixes

    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
     of
    -3.52
     to
    -3.39
     in
    -2.34
     for
    -2.28
     is
    -2.27
     at
    -2.16
     on
    -2.13
     or
    -2.13
     by
    -1.53
     a
    -1.50
    POSITIVE LOGITS
    itize
    1.85
     disposent
    1.78
     {
    
    
    1.75
    珧
    1.70
    forKey
    1.69
     diamantes
    1.65
    vikling
    1.63
    ſſer
    1.62
     devraient
    1.62
     utilisent
    1.61
    Activations Density 0.102%

    No Known Activations