© 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. 22-GEMMASCOPE-RES-131K
    7. 95696
    Prev
    Next
    INDEX
    Explanations

    mathematical and chemical notation

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

    LaTeX mathematical notation, particularly limit expressions in mathematical formulas.

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

    The neuron never fires—i.e. it doesn’t detect any pattern (it’s effectively a “dead” neuron).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     then
    -1.73
    yadh
    -1.71
    睽
    -1.66
     Then
    -1.58
    嘥
    -1.48
     навіть
    -1.45
    Demikian
    -1.45
     Saltar
    -1.44
     abrigo
    -1.43
    eneuve
    -1.43
    POSITIVE LOGITS
    for
    1.51
    b
    1.41
    ge
    1.41
    “
    1.40
    e
    1.39
    ,“
    1.37
    G
    1.36
    “(
    1.36
    te
    1.34
    pa
    1.30
    Activations Density 0.004%

    No Known Activations