© 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. 7172
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and code contexts

    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
     comprising
    -2.73
    ,”
    -2.64
    ↵
    -2.59
    _
    -2.59
    .’
    -2.52
    m
    -2.52
     achieving
    -2.47
     DataTypes
    -2.45
    。”
    -2.44
     compiti
    -2.33
    POSITIVE LOGITS
    
    3.22
     famed
    2.80
    
    2.73
     savvy
    2.67
     usado
    2.67
    
    2.67
    actéristi
    2.66
     คน
    2.64
     REALLY
    2.59
    굼
    2.58
    Activations Density 0.023%

    No Known Activations