© 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. 107122
    Prev
    Next
    INDEX
    Explanations

    Chinese Communist Party

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

    This neuron detects tokens in the lead (opening) lines of Reuters‐style news articles.

    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
     més
    -0.88
    μπο
    -0.84
    总统
    -0.83
    izability
    -0.83
    anía
    -0.82
    Vegeu
    -0.81
    🥑
    -0.81
    ifdef
    -0.79
    ]):
    -0.79
    poort
    -0.79
    POSITIVE LOGITS
     Party
    1.43
     party
    1.41
     CPC
    1.27
     Polit
    1.17
     Communist
    1.14
    Party
    1.13
    習
    1.04
    party
    1.03
     Partei
    1.00
     CCP
    0.99
    Activations Density 0.020%

    No Known Activations