© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81016
    Prev
    Next
    INDEX
    Explanations

    legal, administrative, and technical documents

    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
     الول
    -0.69
     香水
    -0.68
    行政区划
    -0.67
    minyak
    -0.67
     Abstand
    -0.67
    читал
    -0.67
     ribuan
    -0.67
    otte
    -0.66
     Blue
    -0.65
     Gesellschaft
    -0.65
    POSITIVE LOGITS
     Fukushima
    0.95
     Preservation
    0.85
     Benjam
    0.83
    ም
    0.83
    waarden
    0.78
    Navbar
    0.77
    Numerology
    0.77
     pretended
    0.75
     pathogens
    0.75
     Taunton
    0.75
    Activations Density 0.006%

    No Known Activations