© 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. 31091
    Prev
    Next
    INDEX
    Explanations

    umbrella canopies shade shelter

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

    The main thing this neuron does is detect mentions of overhead-shelter terms (e.g. “canopy,” “canopies,” “umbrella”).

    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
    bdb
    -0.75
     меда
    -0.71
    ְב
    -0.69
    ライオン
    -0.68
    umpul
    -0.68
    CONTENTS
    -0.67
    חו
    -0.67
    weck
    -0.66
    тиви
    -0.66
    ciale
    -0.66
    POSITIVE LOGITS
     shelter
    3.16
     canopy
    2.69
     shade
    2.56
     umbrella
    2.55
     shelters
    2.53
     roof
    2.41
     awning
    2.33
     Shelter
    2.27
     sheltered
    2.25
     cover
    2.13
    Activations Density 0.041%

    No Known Activations