© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57342
    Prev
    Next
    INDEX
    Explanations

    political differences and disagreements

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

    This neuron fires on explicit expressions of disagreement or permission to disagree—e.g. phrases like “OK to disagree with someone’s ideas.”

    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
    ⛧
    -0.85
    Ⓞ
    -0.83
    artin
    -0.83
     interrelated
    -0.81
    endaft
    -0.81
     būti
    -0.80
    cés
    -0.79
    iston
    -0.78
     naudoti
    -0.78
    âteau
    -0.78
    POSITIVE LOGITS
     ideological
    2.64
    ideo
    2.41
     ideology
    2.34
     ideologies
    2.06
     ide
    2.05
    Ide
    1.97
     Ide
    1.86
     beliefs
    1.73
     views
    1.73
     Ideology
    1.72
    Activations Density 0.048%

    No Known Activations