© 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. 94262
    Prev
    Next
    INDEX
    Explanations

    generation equipment, program section, advise and assist brigade

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

    The neuron fires on formal military occupational titles or service‐member job/designation phrases.

    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
    Advertisement
    -0.83
    Ст
    -0.80
     PAH
    -0.78
    験
    -0.78
     intru
    -0.77
    Tris
    -0.74
     Advertisement
    -0.74
     δο
    -0.73
    uldig
    -0.73
    rschein
    -0.71
    POSITIVE LOGITS
     friendly
    0.89
     card
    0.81
     live
    0.80
    quiel
    0.78
    ꜣ
    0.78
     Friendly
    0.76
    keto
    0.76
    coach
    0.76
    PositiveButton
    0.75
     counseling
    0.73
    Activations Density 0.018%

    No Known Activations