© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9188
    Prev
    Next
    INDEX
    Explanations

    invitations to talk or discuss

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

    The neuron detects expressions of offering or inviting participation—phrases where someone volunteers, offers, or invites others to join or take something on.

    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
     (
    0.72
     habits
    0.68
     verdicts
    0.67
     hábitos
    0.63
    などで
    0.63
     dentists
    0.59
     drinkers
    0.59
    ”(
    0.58
     vibr
    0.58
    人々
    0.58
    POSITIVE LOGITS
    訌
    0.75
     একটা
    0.68
     Extension
    0.68
    帮忙
    0.68
     केटी
    0.66
     ट्रेनिंग
    0.65
     Invitational
    0.65
     Internship
    0.64
     पेशकश
    0.64
     Modelling
    0.64
    Activations Density 0.064%

    No Known Activations