© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6412
    Prev
    Next
    INDEX
    Explanations

    collaboration and integration

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

    The neuron fires on phrases expressing collaboration or partnership (e.g. “partner with,” “work with,” “partnerships with”).

    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
     quitting
    0.71
     undulating
    0.70
     riveting
    0.70
    ὃ
    0.68
    而且
    0.68
     dismissal
    0.67
     عندهم
    0.67
     preoccupation
    0.67
    ἃ
    0.67
     theorem
    0.64
    POSITIVE LOGITS
     partners
    1.48
     stakeholders
    1.43
     партне
    1.40
     partenaires
    1.34
    partners
    1.32
     अन्य
    1.27
    合作伙伴
    1.27
     Partners
    1.25
     colleagues
    1.23
     collaborators
    1.23
    Activations Density 0.588%

    No Known Activations