© 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. 45291
    Prev
    Next
    INDEX
    Explanations

    biological tissue properties and interactions

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

    mentions of tissue or anatomical structures in medical or surgical contexts.

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

    The neuron detects highly technical, domain‐specific medical/surgical terminology—especially nouns referring to instruments, tissues, procedures, and related apparatus.

    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
    (_.
    -0.81
     поши
    -0.71
    ногие
    -0.71
     đỏ
    -0.69
     IMO
    -0.68
    SourceChecksum
    -0.67
    MainFrame
    -0.67
     Schwä
    -0.66
     👌
    -0.65
    жены
    -0.64
    POSITIVE LOGITS
     tissues
    3.70
     tissue
    3.67
    tissue
    2.58
     Tissues
    2.55
     Tissue
    2.47
    Tissue
    2.34
    tiss
    2.23
     tissus
    2.08
     structures
    1.88
     tejidos
    1.88
    Activations Density 0.210%

    No Known Activations