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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11339
    Prev
    Next
    INDEX
    Explanations

    politics and community development

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

    The neuron fires on scholarly or policy‐oriented terms—especially vocabulary from political science and international security (e.g. security, politics, comparative, development, community, organizations).

    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
     vernis
    -1.43
    淠
    -1.36
     hamil
    -1.35
     aveo
    -1.33
    ную
    -1.30
     fuma
    -1.30
     描
    -1.30
    chased
    -1.29
     capitan
    -1.29
    ceased
    -1.28
    POSITIVE LOGITS
     in
    1.33
     
    1.20
    -
    1.13
     and
    1.09
    сных
    1.06
     framing
    1.02
    ,
    1.01
     utilizó
    1.00
     locals
    1.00
     míst
    1.00
    Activations Density 0.127%

    No Known Activations