© 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. 11834
    Prev
    Next
    INDEX
    Explanations

    QM chemistry and scientific terms

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

    scientific or technical notation in documents related to chemistry, quantum mechanics, and computational modeling.

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

    The neuron activates on numeric tokens (sequences of digits), i.e. it detects numbers.

    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
    торами
    -0.78
     warmen
    -0.70
    explode
    -0.69
    𝙲
    -0.69
     consequently
    -0.68
     Burroughs
    -0.67
     台灣
    -0.67
    復興
    -0.67
    شاف
    -0.66
     contacted
    -0.66
    POSITIVE LOGITS
     atoms
    0.96
     coordinates
    0.95
     species
    0.95
     nat
    0.94
     CONFIG
    0.94
     configurations
    0.93
    atomic
    0.91
     atom
    0.91
     XYZ
    0.91
     Nat
    0.90
    Activations Density 0.017%

    No Known Activations