© 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. 81372
    Prev
    Next
    INDEX
    Explanations

    fuel injection or delivery

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

    The neuron strongly fires on technical mentions of specialized fuel‐system components (e.g. “Aeromotive Inline Fuel Filter,” flow “micron” ratings, fuel delivery parts, and related manufacturer names).

    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
    🕔
    -0.80
     Humidity
    -0.79
    ättning
    -0.79
    ହ
    -0.75
     Pliny
    -0.75
     채
    -0.74
     aloof
    -0.74
    獼
    -0.73
    PEACE
    -0.73
    Conflicts
    -0.72
    POSITIVE LOGITS
     fuel
    1.93
     Fuel
    1.57
    Fuel
    1.52
    fuel
    1.46
    FUEL
    1.27
     топли
    1.22
    tank
    1.16
     FUEL
    1.16
     fuels
    1.13
     pump
    1.12
    Activations Density 0.020%

    No Known Activations