© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32067
    Prev
    Next
    INDEX
    Explanations

    roadside assistance for vehicle breakdown

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

    The main thing this neuron does is find mentions of vehicles in distress or emergency (breakdowns, stranded motorists, collisions, etc.).

    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
    őle
    -0.80
    予選
    -0.78
    ónimo
    -0.76
    onets
    -0.74
    ឃ
    -0.73
    オープン
    -0.73
    дации
    -0.72
     remodeled
    -0.72
    referer
    -0.72
    槍
    -0.70
    POSITIVE LOGITS
     roadside
    3.14
     breakdown
    2.45
     Breakdown
    1.95
    breakdown
    1.89
     breakdowns
    1.80
    Breakdown
    1.70
     Road
    1.61
     jump
    1.58
     emergency
    1.52
    Road
    1.50
    Activations Density 0.024%

    No Known Activations