© 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. 79463
    Prev
    Next
    INDEX
    Explanations

    pilot flame ignition

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

    This neuron detects technical domain–specific terms for gas‐fired water‐heater and combustion‐chamber components.

    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
    mpz
    -0.81
    wohnungen
    -0.80
     kalend
    -0.77
    вки
    -0.75
    toContain
    -0.75
    nisk
    -0.74
     Jadi
    -0.74
    Constru
    -0.72
    responseText
    -0.72
     brackish
    -0.70
    POSITIVE LOGITS
     pilot
    1.09
    pilot
    0.94
     safety
    0.93
     limit
    0.93
     flames
    0.91
     trial
    0.90
     flame
    0.90
     Pilot
    0.89
    Pilot
    0.88
     ign
    0.88
    Activations Density 0.007%

    No Known Activations