© 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. 60524
    Prev
    Next
    INDEX
    Explanations

    numbers and chemical suffixes

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

    chemical compound structures with rings or cyclic molecular formations.

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

    The neuron strongly activates on numeric locants and hyphenated digits used in systematic chemical compound names.

    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
     take
    -3.36
     takes
    -2.95
    take
    -2.88
    Take
    -2.80
    Takes
    -2.73
    takes
    -2.69
     took
    -2.66
     Takes
    -2.64
     taking
    -2.61
     TAKE
    -2.58
    POSITIVE LOGITS
    قف
    0.78
    يمي
    0.71
     общем
    0.71
     Большой
    0.68
    idung
    0.68
     caroten
    0.68
     ''}
    0.66
    🚖
    0.66
    PLAINT
    0.66
    carry
    0.65
    Activations Density 0.107%

    No Known Activations