© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49820
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and numbers

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

    numeric identifiers and chemical reference numbers in scientific or patent documents.

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

    The neuron specializes in spotting numeric tokens and formatted number‐heavy identifiers (e.g., compound or patent numbers and related numeric markers).

    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
    xpos
    -0.85
    dataSet
    -0.82
     Tid
    -0.79
    ější
    -0.78
     Metacritic
    -0.77
    動く
    -0.77
     Лев
    -0.76
     thérape
    -0.76
    窕
    -0.75
    ად
    -0.75
    POSITIVE LOGITS
     ester
    0.90
     infrared
    0.87
     Ester
    0.85
    anoic
    0.83
    infrared
    0.82
    onica
    0.79
    様でした
    0.79
     steam
    0.79
    ֤
    0.78
    qué
    0.77
    Activations Density 0.002%

    No Known Activations