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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59644
    Prev
    Next
    INDEX
    Explanations

    political ideologies and affiliations

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

    The neuron activates on words naming political ideologies or factions (e.g. conservative, liberal, Whig, etc.).

    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
     inaugura
    -1.09
    おわりに
    -1.00
    
    -0.99
     voto
    -0.97
     amplific
    -0.94
     phénom
    -0.94
     distanci
    -0.93
     ambassade
    -0.91
     cytometry
    -0.90
    giày
    -0.90
    POSITIVE LOGITS
     tendencies
    1.47
     sentiments
    1.23
     sentiment
    1.20
     movement
    1.16
     impulse
    1.09
     leaning
    1.06
     inclined
    1.02
     тенден
    1.02
     ideas
    0.95
     खे
    0.94
    Activations Density 0.053%

    No Known Activations