© 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. 10-GEMMASCOPE-RES-131K
    7. 103340
    Prev
    Next
    INDEX
    Explanations

    electrical resistor and inductor

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

    This neuron detects mentions of passive circuit components—most strongly the word “resistor” (and to a lesser extent similar parts like inductors).

    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
    ia
    -2.47
    
    -2.45
     adventures
    -2.44
    ſſer
    -2.42
     beinhaltet
    -2.39
     некоторых
    -2.34
     overarching
    -2.34
     dekoratif
    -2.33
     этого
    -2.30
    ญี่ป
    -2.28
    POSITIVE LOGITS
    </i>
    3.39
    </h1>
    2.69
    ため
    2.33
     It
    2.13
    >
    2.05
     стал
    2.03
    </h3>
    2.02
     良い
    1.95
    🍺
    1.93
     欣赏
    1.91
    Activations Density 0.003%

    No Known Activations