© 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. 78503
    Prev
    Next
    INDEX
    Explanations

    civil followed by society or liberties

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

    The neuron detects the word “civil” (especially in phrases like civil society or civil liberties), marking references to civil institutions or contexts.

    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
     religious
    -0.85
    kier
    -0.84
     Alto
    -0.81
     ۲
    -0.75
    НОСТИ
    -0.75
    religious
    -0.72
    olski
    -0.70
     tank
    -0.70
    ثم
    -0.70
    ッと
    -0.69
    POSITIVE LOGITS
     society
    1.56
     Society
    1.41
    society
    1.40
     SOCIETY
    1.37
    Society
    1.34
     sociedad
    1.16
     società
    1.16
     société
    1.14
     sociedade
    0.94
     Sociedade
    0.91
    Activations Density 0.021%

    No Known Activations