© 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. 59667
    Prev
    Next
    INDEX
    Explanations

    scientific, biological, and environmental terms

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

    scientific notation, particularly numerical values and measurements in academic or research papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on capitalized scientific terms (proper names and acronyms) and numeric expressions (measurements and units).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     RESIDENCE
    -0.76
    latlng
    -0.71
     трубо
    -0.69
    钤
    -0.68
    Residence
    -0.68
    Cnt
    -0.67
     Duque
    -0.67
     fume
    -0.67
     Schott
    -0.66
     Saber
    -0.66
    POSITIVE LOGITS
     shower
    1.08
     showers
    1.01
    ankle
    0.94
     ankle
    0.91
     air
    0.88
    CORS
    0.88
     Auger
    0.85
     CORS
    0.83
     atmospheric
    0.83
     primaries
    0.82
    Activations Density 0.017%

    No Known Activations