© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99138
    Prev
    Next
    INDEX
    Explanations

    scientific abbreviations and notations

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers that appear in scientific and technical contexts, particularly when displaying measurements, dates, or numerical data points.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     some
    -0.81
    美味しい
    -0.79
    JOUR
    -0.77
    зина
    -0.74
    couverte
    -0.74
    لالة
    -0.74
    gefahr
    -0.74
     اج
    -0.71
    fiq
    -0.71
    맛
    -0.71
    POSITIVE LOGITS
    でもある
    0.94
     bouts
    0.84
    
    0.83
     Ngb
    0.82
    ைய
    0.80
     PERCENT
    0.79
    selaer
    0.78
     .,
    0.78
    Lähde
    0.78
     потому
    0.77
    Activations Density 0.013%

    No Known Activations