© 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. 48381
    Prev
    Next
    INDEX
    Explanations

    high voltage applications

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

    This neuron detects mentions of “voltage,” especially in high-voltage contexts or voltage measurements.

    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
     Redacción
    -1.51
    ahhh
    -1.46
    ecause
    -1.46
    Opinión
    -1.46
    T
    -1.43
     lahat
    -1.40
    álise
    -1.40
     階
    -1.38
     ビーチ
    -1.36
     Traducción
    -1.35
    POSITIVE LOGITS
     और
    1.75
    and
    1.55
    Hochspringen
    1.52
     область
    1.51
    媄
    1.50
    向了
    1.47
     memand
    1.42
     étoit
    1.38
    AP
    1.38
    潆
    1.37
    Activations Density 0.016%

    No Known Activations