© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84371
    Prev
    Next
    INDEX
    Explanations

    lymph nodes, bronchitis

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

    medical conditions and anatomical terms, especially related to respiratory system and lymphatic system.

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

    The neuron flags prominent domain-specific topic nouns (e.g. place names, chemical materials, medical conditions) that serve as the central subject of a passage.

    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
     Now
    -2.95
    ឪ
    -2.84
     the
    -2.63
    翃
    -2.63
     Commonly
    -2.63
    2
    -2.56
     soothe
    -2.55
     Это
    -2.55
     This
    -2.50
     Сейчас
    -2.47
    POSITIVE LOGITS
    es
    3.03
    橚
    2.81
    葙
    2.75
    櫚
    2.70
     marea
    2.52
    踽
    2.48
    茕
    2.48
    呖
    2.48
    蚍
    2.45
    ?”
    2.44
    Activations Density 0.027%

    No Known Activations