© 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. 10-GEMMASCOPE-RES-131K
    7. 103049
    Prev
    Next
    INDEX
    Explanations

    section identifiers

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

    numerical references to legal sections, subsections, or statutory provisions in formal documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron fires on numeric references to legal or document sections (section numbers, clause numbers, or similar numbered citations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    皛
    -2.30
    sukienka
    -2.13
    
    -2.02
    旆
    -1.97
     comunión
    -1.92
    ケモン
    -1.89
    ᥬ
    -1.89
    鬩
    -1.88
    ſche
    -1.86
    鹪
    -1.86
    POSITIVE LOGITS
    il
    2.70
    (
    2.59
     of
    2.53
     \
    2.27
    ↵↵
    2.20
    ↵
    2.20
    O
    2.14
    U
    2.14
    》。
    2.11
    \
    2.06
    Activations Density 0.016%

    No Known Activations