© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6303
    Prev
    Next
    INDEX
    Explanations

    Community engagement and spirit

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

    The neuron detects mentions of community‐oriented concepts, especially the word “community” or closely connected compound forms (e.g. “community-engaged,” “participatory community”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     اه
    0.69
     الاح
    0.69
    اه
    0.67
     swamp
    0.67
     sketchy
    0.65
     whine
    0.63
    ੰ
    0.63
    审查
    0.63
    ارس
    0.63
     crumbling
    0.62
    POSITIVE LOGITS
    community
    1.21
    Community
    1.20
     Community
    1.20
     comunitario
    1.06
    社区
    1.05
     komunitas
    1.02
     COMMUNITY
    0.98
     comunidades
    0.97
     community
    0.95
    社區
    0.95
    Activations Density 0.131%

    No Known Activations