© 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. 117458
    Prev
    Next
    INDEX
    Explanations

    modelsystem and cell models

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

    This neuron is looking for examples or instances of model systems in scientific research.

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

    The neuron fires on technical/scientific terminology—words like “system,” “model,” “measure,” “dynamical,” etc.—marking academic or research‐style content.

    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
    즌
    -0.76
    atically
    -0.73
    érés
    -0.72
    殤
    -0.71
     Jahr
    -0.69
    واء
    -0.69
    }}}\
    -0.69
    TODOS
    -0.68
    ATED
    -0.68
    ientí
    -0.68
    POSITIVE LOGITS
     system
    8.50
     systems
    6.22
    system
    5.94
     sistema
    5.75
    系统
    5.59
    システム
    5.56
     système
    5.34
     система
    5.25
     System
    4.91
    SYSTEM
    4.91
    Activations Density 0.512%

    No Known Activations