© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62653
    Prev
    Next
    INDEX
    Explanations

    smoke detectors and alarms

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

    The neuron consistently activates on the word “smoke” (in any casing or when part of hyphenated/compound forms).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    那些
    -0.84
    6
    -0.79
    .”
    -0.77
    .…
    -0.75
    造成
    -0.75
     хок
    -0.75
     spent
    -0.75
     brasileño
    -0.74
    as
    -0.73
    وقع
    -0.72
    POSITIVE LOGITS
     Signals
    1.25
     inhalation
    1.05
    signals
    0.95
    Signals
    0.94
    ͓
    0.90
     alarms
    0.90
    umd
    0.88
     cessation
    0.88
    しますが
    0.88
    vantaged
    0.88
    Activations Density 0.014%

    No Known Activations