© 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. 10-GEMMASCOPE-RES-131K
    7. 1636
    Prev
    Next
    INDEX
    Explanations

    biophysical properties and techniques

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

    The neuron detects scientific terms related to physics, particularly in academic journal articles and scientific publications.

    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_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
    '
    -2.92
    ar
    -2.06
    Y
    -1.89
    C
    -1.82
    /
    -1.80
    To
    -1.73
    ."
    -1.67
    S
    -1.66
    P
    -1.66
    man
    -1.64
    POSITIVE LOGITS
    鹟
    1.94
     desafios
    1.91
     yaşad
    1.91
     empêche
    1.88
    GEBUR
    1.87
     ſch
    1.84
    
    1.82
    厛
    1.80
    也会
    1.73
    摃
    1.73
    Activations Density 0.006%

    No Known Activations