© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57391
    Prev
    Next
    INDEX
    Explanations

    organometallic chemistry and catalysis

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

    chemistry-related technical terminology, particularly involving metal complexes and chemical reactions.

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

    The neuron’s primary function is to detect numeric tokens (Arabic numerals) in the text.

    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
     sulfate
    -0.71
    XtraReports
    -0.71
     hilfiger
    -0.69
    wanych
    -0.69
     تخم
    -0.68
    จีน
    -0.68
     AGENTS
    -0.68
     }}{\
    -0.68
    ạn
    -0.68
     Kriminal
    -0.67
    POSITIVE LOGITS
     Cp
    1.00
     organ
    0.91
    '(
    0.85
     CVD
    0.85
    prec
    0.81
    essori
    0.81
    вѣ
    0.80
     Organ
    0.80
     gas
    0.79
     marina
    0.77
    Activations Density 0.105%

    No Known Activations