© 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. 10-GEMMASCOPE-RES-131K
    7. 128520
    Prev
    Next
    INDEX
    Explanations

    libertarian, anarchist, ism

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

    The neuron activates on words naming political or ideological movements and their “-ism” or group labels (e.g. conservative, libertarian, anarchist, Paleo, cypherpunk, Extropian).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    蟜
    -1.86
    PvB
    -1.84
    
    -1.78
    旆
    -1.72
    StoryboardSegue
    -1.67
    ть
    -1.63
    ༛
    -1.60
     plupart
    -1.58
    哢
    -1.56
    زشکی
    -1.55
    POSITIVE LOGITS
    」
    1.57
    J
    1.50
    ↵↵
    1.49
    R
    1.48
    🢒
    1.46
    but
    1.45
    其
    1.44
     and
    1.41
     do
    1.41
    SS
    1.37
    Activations Density 0.018%

    No Known Activations