© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25669
    Prev
    Next
    INDEX
    Explanations

    division and polarization

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

    content related to political division, polarization, and social tensions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires strongly on words and phrases related to division or polarization (e.g. divide, divided, polarization).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     révé
    -0.95
    ḿ
    -0.93
    %%%%%%%%%
    -0.93
    Compress
    -0.85
     partenaire
    -0.82
     préoccup
    -0.82
     municípios
    -0.82
     kooper
    -0.82
     lumineux
    -0.81
    şık
    -0.79
    POSITIVE LOGITS
     divisive
    2.17
     divide
    1.99
     polar
    1.98
     division
    1.88
     polarization
    1.75
     divides
    1.73
     dividing
    1.71
     instig
    1.70
     inflammatory
    1.67
     divisions
    1.66
    Activations Density 0.036%

    No Known Activations