© 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. 3646
    Prev
    Next
    INDEX
    Explanations

    computer hardware connections

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

    The neuron strongly activates on uppercase technical acronyms and interface identifiers (e.g. USB, DP, DVI, .h, Thunderbolt).

    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
     setUser
    -0.91
    炮
    -0.84
    砲
    -0.79
    Cox
    -0.78
    eabouts
    -0.78
     Tales
    -0.77
    intar
    -0.76
    cora
    -0.75
    kli
    -0.74
    dampak
    -0.74
    POSITIVE LOGITS
     PD
    1.04
     Thunderbolt
    1.03
    Display
    0.84
     Display
    0.82
     arvo
    0.79
    видео
    0.77
     DisplayPort
    0.76
    Thunder
    0.74
    视频
    0.72
     видео
    0.72
    Activations Density 0.020%

    No Known Activations