© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77358
    Prev
    Next
    INDEX
    Explanations

    eaves, gutters, fascia

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

    The neuron detects architectural descriptions of bracket‐supported eaves or similar structural overhang elements on buildings.

    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
     rijk
    -0.81
     bode
    -0.81
    ataires
    -0.80
    LAY
    -0.79
    gram
    -0.77
    antaine
    -0.73
    haltet
    -0.73
    pam
    -0.72
    sdk
    -0.72
     比
    -0.72
    POSITIVE LOGITS
     gutter
    2.03
     gutters
    1.89
     Gutter
    1.73
    gutter
    1.68
     fascia
    1.20
     Gut
    1.13
     GUT
    1.07
     rainwater
    0.99
     downs
    0.98
     soff
    0.94
    Activations Density 0.005%

    No Known Activations