© 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. 34-GEMMASCOPE-RES-131K
    7. 53826
    Prev
    Next
    INDEX
    Explanations

    units and chemical quantities

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

    mathematical notation and scientific/technical symbols in academic or educational content.

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

    The neuron specializes in spotting fragments of inline mathematical notation (variable names, Greek-letter tokens, operators like “=”, “–”, etc., and math symbols).

    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
     espirituales
    -0.96
    Sisters
    -0.92
     Compared
    -0.90
    Without
    -0.90
    滙
    -0.86
     enfans
    -0.84
    就行了
    -0.82
    権利
    -0.82
    égio
    -0.82
     факторов
    -0.82
    POSITIVE LOGITS
    Digits
    0.98
     mol
    0.88
     moles
    0.87
     Derry
    0.86
     Дер
    0.85
     molar
    0.84
     IUPAC
    0.84
    ℳ
    0.84
    sung
    0.83
     UNITS
    0.83
    Activations Density 0.005%

    No Known Activations