© 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. 10-GEMMASCOPE-RES-131K
    4. 99802
    Prev
    Next
    INDEX
    Explanations

    rotor, flywheel, crankshaft, pulley

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

    The neuron activates on specialized mechanical‐engineering component terms (e.g. magneto, generator, flywheel, crankshaft, rotor).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     CONCEP
    -1.51
     mengakui
    -1.50
     estavam
    -1.48
    鸨
    -1.45
     espectro
    -1.44
     relativi
    -1.42
     rengi
    -1.42
     extranjera
    -1.40
    années
    -1.39
    がついて
    -1.38
    POSITIVE LOGITS
    </strong>
    1.85
     который
    1.62
    </h4>
    1.62
    </h3>
    1.47
    </h2>
    1.42
    单个
    1.36
     be
    1.36
    日记
    1.34
     и
    1.33
     intuitively
    1.33
    Activations Density 0.066%

    No Known Activations