© 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. 84059
    Prev
    Next
    INDEX
    Explanations

    fluids and gases

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

    The neuron fires on the highly technical, procedural language you find in mechanical‐engineering patent descriptions (e.g. terms like “section,” “operation,” “pressurized,” “cooling,” “generate,” 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
    OnItem
    -0.80
    corder
    -0.77
    parseFloat
    -0.77
    rupal
    -0.75
     restTemplate
    -0.75
    
    -0.74
    寒冷
    -0.73
    ┫
    -0.73
    ):}
    -0.73
    requestBody
    -0.73
    POSITIVE LOGITS
     water
    2.13
     fluids
    1.88
     seawater
    1.70
     gases
    1.63
     liquids
    1.59
     rainwater
    1.55
     fluid
    1.46
     liquid
    1.43
     coolant
    1.41
     água
    1.40
    Activations Density 0.316%

    No Known Activations