© 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. 115435
    Prev
    Next
    INDEX
    Explanations

    chemical nomenclature and numbers

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

    legal court citation patterns and scientific notation with numerical identifiers.

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

    This neuron detects formal numbered identifiers—especially legal docket or case numbers (e.g. “No. 05-19-00375-…,” court district citations) and similar numeric‐code sequences.

    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
    Ő
    -0.83
    metis
    -0.78
     Villanueva
    -0.77
     simplement
    -0.75
    äng
    -0.75
    రం
    -0.74
    所に
    -0.73
     Consist
    -0.72
    上角
    -0.72
     забу
    -0.72
    POSITIVE LOGITS
     menschliche
    0.87
    část
    0.82
    kező
    0.82
     keen
    0.79
     marea
    0.77
     provas
    0.75
    アイス
    0.74
    Keen
    0.73
     denote
    0.73
    Matériau
    0.73
    Activations Density 0.239%

    No Known Activations