© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98040
    Prev
    Next
    INDEX
    Explanations

    emergency response teams

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

    The neuron fires strongly on descriptions of wildfire incidents and their containment progress—terms like “fire,” “containment,” “firefighters,” and the accompanying percentages or numeric progress markers.

    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
     девочек
    -1.11
    ulica
    -1.02
    polic
    -1.02
    김
    -0.99
     remodeling
    -0.98
     légales
    -0.95
    Τ
    -0.95
    产品
    -0.94
     cupboard
    -0.93
    kung
    -0.91
    POSITIVE LOGITS
     yesterday
    1.48
     teams
    1.38
     techniques
    1.36
     equipment
    1.34
     manually
    1.29
     specialists
    1.28
     crews
    1.27
     Wednesday
    1.27
     Tuesday
    1.21
     operations
    1.20
    Activations Density 0.036%

    No Known Activations