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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81222
    Prev
    Next
    INDEX
    Explanations

    LaTeX document formatting

    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_34/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
     Sleeves
    -0.79
     prefix
    -0.78
     attached
    -0.74
     combined
    -0.73
     quickly
    -0.72
     Hot
    -0.72
     Function
    -0.71
     Geburtstag
    -0.70
     trăng
    -0.69
    toPromise
    -0.68
    POSITIVE LOGITS
     ""}
    0.99
     yaprak
    0.93
    Encoding
    0.88
     ''}
    0.87
     comprensión
    0.87
    latLng
    0.86
    匆
    0.85
     morire
    0.85
    ÍTULO
    0.85
    THEY
    0.85
    Activations Density 0.002%

    No Known Activations