© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10328
    Prev
    Next
    INDEX
    Explanations

    team or groups

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

    This neuron strongly activates on mentions of “team” (especially in “team of …” or similar teamwork contexts).

    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_24_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
    ש
    1.43
     użyt
    1.27
    einander
    1.15
    ̣t
    1.12
     kraja
    1.12
     vrch
    1.11
    um
    1.09
    lerde
    1.07
    かで
    1.07
    ču
    1.06
    POSITIVE LOGITS
    م
    1.49
     TEAM
    1.45
     Team
    1.31
    ৮
    1.27
    Team
    1.26
    та
    1.17
    TEAM
    1.17
    ים
    1.16
    ה
    1.16
    ान
    1.09
    Activations Density 0.120%

    No Known Activations