© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107808
    Prev
    Next
    INDEX
    Explanations

    particulate matter

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

    scientific or academic citations and references in scholarly papers.

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

    This neuron fires on tokens that appear in formal scientific‐paper content—e.g. section headings, title words, reference markers, and other metadata in academic articles.

    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
     flood
    -0.97
    flood
    -0.81
     abrupt
    -0.79
     temperaturas
    -0.79
    }}}}
    -0.79
    belief
    -0.79
    UKAN
    -0.78
     pickle
    -0.77
     temperature
    -0.76
    ossa
    -0.76
    POSITIVE LOGITS
     Seinfeld
    1.13
     Atmospheric
    0.85
     atmos
    0.84
     smog
    0.84
     aerodynamic
    0.81
     Emissions
    0.81
     Atmos
    0.80
     airborne
    0.77
     Breathe
    0.76
    Atmospheric
    0.76
    Activations Density 0.010%

    No Known Activations