© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107792
    Prev
    Next
    INDEX
    Explanations

    firefighter, firemen, and related roles

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

    The neuron fires strongly on mentions of firefighters and fire‐service–related terms.

    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
    Sailing
    -1.05
     ادبی
    -0.94
    jeuner
    -0.92
     Sculpture
    -0.81
    Sculpture
    -0.79
     missiles
    -0.78
     България
    -0.78
     boule
    -0.78
     delightful
    -0.77
    ftar
    -0.77
    POSITIVE LOGITS
     fire
    2.80
     Fire
    2.59
     firefighter
    2.50
     firefighters
    2.44
    Fire
    2.28
     firemen
    2.00
    消防
    1.98
    fire
    1.94
     fireman
    1.92
     firefighting
    1.86
    Activations Density 0.049%

    No Known Activations