© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56903
    Prev
    Next
    INDEX
    Explanations

    USB and connected devices

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

    The neuron detects mentions of “USB” (and related USB‐prefixed device tokens).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    薄い
    -1.02
    joueur
    -0.93
    bisous
    -0.84
    訁
    -0.84
     maravilhoso
    -0.83
     unn
    -0.82
     amazing
    -0.82
     refuer
    -0.76
     تأثير
    -0.76
    citrus
    -0.75
    POSITIVE LOGITS
    textwidth
    1.02
    听到了
    0.99
    noteq
    0.94
     娘
    0.89
    trique
    0.86
    当た
    0.84
    enum
    0.84
    撵
    0.83
     adopts
    0.83
    $<
    0.82
    Activations Density 0.012%

    No Known Activations