© 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. 21474
    Prev
    Next
    INDEX
    Explanations

    region and zone

    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
    
    -2.14
     formatos
    -1.98
     内衣
    -1.96
     représenter
    -1.94
    槼
    -1.91
    鹩
    -1.87
    aziland
    -1.85
     motocicletas
    -1.84
     obrazy
    -1.81
    もありますが
    -1.71
    POSITIVE LOGITS
     of
    2.34
    (
    2.28
    at
    2.02
     area
    1.95
     `
    1.89
     :
    1.74
    E
    1.68
    eng
    1.65
     «
    1.61
    ."
    1.59
    Activations Density 0.076%

    No Known Activations