© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118085
    Prev
    Next
    INDEX
    Explanations

    anatomical regions or organs

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

    This neuron identifies anatomical terms related to body organs and tissues, particularly focusing on internal organs like the lung, stomach, intestines, colon, and brain regions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     paysages
    -1.02
    今度
    -1.02
    ificaciones
    -0.99
    現在
    -0.96
    今も
    -0.93
     amorosa
    -0.93
     Bewußt
    -0.92
     باش
    -0.91
     utilisés
    -0.91
     nuits
    -0.90
    POSITIVE LOGITS
     region
    2.06
     région
    1.38
     regions
    1.32
    region
    1.29
     tissues
    1.27
     región
    1.24
     area
    1.21
     of
    1.17
     complex
    1.14
     system
    1.02
    Activations Density 0.359%

    No Known Activations