© 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. 47294
    Prev
    Next
    INDEX
    Explanations

    Q:CT Callbcm, CTC

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

    The neuron fires on short uppercase letter sequences—that is, on two‐ (or similar) letter acronyms or initialisms.

    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
    hloromethane
    -0.74
     Bryn
    -0.74
     싶
    -0.73
     CNT
    -0.72
     sarana
    -0.68
    細節
    -0.68
    딪
    -0.66
    cetta
    -0.66
     rédaction
    -0.65
    CppCodeGen
    -0.65
    POSITIVE LOGITS
    Closeable
    0.97
    resti
    0.86
    Resource
    0.83
    ScrollBar
    0.82
    itectura
    0.82
     Economy
    0.81
    йте
    0.81
     sente
    0.81
     indiri
    0.80
    haling
    0.80
    Activations Density 0.000%

    No Known Activations