© 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. 65812
    Prev
    Next
    INDEX
    Explanations

    storage and supply of fluids

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

    The neuron is looking for technical substance or working-fluid terms (e.g. fuel, water, oil, hydraulic fluid, steam, vapor, ink) in the text.

    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
    fuls
    -0.93
     REPAIR
    -0.85
    hows
    -0.85
     certains
    -0.82
     appartiennent
    -0.81
    zq
    -0.80
    ricts
    -0.79
     espanhol
    -0.79
     maquin
    -0.78
    洗浄
    -0.77
    POSITIVE LOGITS
     handling
    1.04
     supply
    1.02
     holder
    1.02
     delivery
    0.96
     storage
    0.95
     indiscrimin
    0.92
     containment
    0.91
     quantit
    0.91
     պ
    0.87
     holders
    0.86
    Activations Density 0.110%

    No Known Activations