© 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. 22-GEMMASCOPE-RES-131K
    7. 129086
    Prev
    Next
    INDEX
    Explanations

    demonstrative to projects or content

    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
     kteří
    -1.05
    ỳnh
    -1.02
    STRUCTOR
    -1.02
    
    -1.00
     Saludos
    -0.99
    gings
    -0.98
    paramString
    -0.96
    
    -0.96
    Сы
    -0.95
    
    -0.94
    POSITIVE LOGITS
     This
    1.22
     in
    1.19
     on
    1.13
     last
    1.09
     originalmente
    1.05
     because
    1.02
     هذا
    0.99
     for
    0.98
     originally
    0.98
    this
    0.97
    Activations Density 0.063%

    No Known Activations