© 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. 106173
    Prev
    Next
    INDEX
    Explanations

    government and judiciary

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

    The neuron strongly responds to common English function words (especially definite articles, conjunctions, and prepositions).

    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
     político
    -1.03
     autoridades
    -1.01
     autorités
    -1.00
    esModule
    -0.94
    mentação
    -0.93
    laught
    -0.89
    裃
    -0.88
    LayoutPanel
    -0.88
    ष्ठ
    -0.87
     grupa
    -0.87
    POSITIVE LOGITS
     judiciary
    2.02
     police
    1.78
     army
    1.66
     judicial
    1.64
     executive
    1.63
     Supreme
    1.59
     judges
    1.51
     courts
    1.45
     military
    1.42
     Executive
    1.38
    Activations Density 0.044%

    No Known Activations