© 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. 38257
    Prev
    Next
    INDEX
    Explanations

    turbine and compressor components

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

    The neuron is highly sensitive to technical patent‐style descriptions of gas turbine engines and their specific components (e.g. compressor sections, turbine vanes, blades, seals).

    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
    俐
    -0.81
    лакти
    -0.80
     Princess
    -0.78
     invite
    -0.77
     princess
    -0.77
    Hinweise
    -0.75
    undam
    -0.74
    racene
    -0.72
    Invite
    -0.71
     useCallback
    -0.71
    POSITIVE LOGITS
     blade
    1.40
    blade
    1.20
     blades
    1.11
     compressor
    1.09
     Blade
    1.06
    Blade
    1.04
     лопа
    1.03
     Blades
    0.98
    Compressor
    0.92
     Compressor
    0.92
    Activations Density 0.070%

    No Known Activations