© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63905
    Prev
    Next
    INDEX
    Explanations

    nervous system

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

    references to the nervous system, particularly in medical or scientific contexts.

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

    This neuron detects mentions of the nervous system and related neuro-anatomical terms.

    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
    hiel
    -0.80
    checkNotNull
    -0.79
     resolutely
    -0.77
    Früh
    -0.76
     taş
    -0.75
     Nasser
    -0.75
    Lato
    -0.74
    "]);
    -0.73
    𝔲
    -0.73
    𝗄
    -0.71
    POSITIVE LOGITS
     system
    3.06
     System
    1.89
    system
    1.81
     système
    1.49
    System
    1.47
    系统
    1.45
     systeem
    1.38
    システム
    1.35
     sistem
    1.33
     систему
    1.30
    Activations Density 0.090%

    No Known Activations