© 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. 79540
    Prev
    Next
    INDEX
    Explanations

    protestors and action

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

    The neuron is detecting terms that refer to public protests or demonstrations.

    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
    imek
    -1.02
    ֽ
    -1.01
     variation
    -0.94
     giocatore
    -0.93
     verir
    -0.90
     feront
    -0.87
     recruit
    -0.86
    emment
    -0.85
     hesitation
    -0.85
    ޏ
    -0.83
    POSITIVE LOGITS
     staged
    1.52
     staging
    1.30
     protest
    1.18
     gathered
    1.17
     congreg
    1.15
    Staging
    1.15
     protested
    1.09
    staging
    1.09
     stages
    1.09
     stage
    1.08
    Activations Density 0.048%

    No Known Activations