© 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. 107707
    Prev
    Next
    INDEX
    Explanations

    ANSI and IEEE standards

    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
    easeOut
    -0.93
    جة
    -0.77
     cuore
    -0.75
     hemisphere
    -0.73
    لاح
    -0.73
     fire
    -0.72
     εφ
    -0.70
     plate
    -0.70
     obviously
    -0.69
    友好
    -0.69
    POSITIVE LOGITS
     ANSI
    1.20
     standards
    1.02
    ANSI
    1.00
     Standards
    0.95
    AMERICAN
    0.93
     American
    0.93
     Accredited
    0.90
    American
    0.89
     американ
    0.88
     committees
    0.85
    Activations Density 0.031%

    No Known Activations