© 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. 47143
    Prev
    Next
    INDEX
    Explanations

    Tata Steel, consultancy, institute

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

    The neuron strongly responds to any token containing the letter sequence “T A T” (e.g. “Tata,” “TAT,” “Tat”)—often in company or protein names.

    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
    médi
    -0.76
    XXV
    -0.75
     sélections
    -0.73
    gabri
    -0.73
     zlat
    -0.72
    median
    -0.72
     perfección
    -0.70
     取り付け
    -0.69
    Yuk
    -0.69
     Debugging
    -0.67
    POSITIVE LOGITS
     motors
    1.11
     Motors
    1.02
     Sons
    0.98
     Consultancy
    0.98
     consultancy
    0.96
    Motors
    0.86
     Circles
    0.85
    okay
    0.81
     tea
    0.79
     institute
    0.79
    Activations Density 0.025%

    No Known Activations