© 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. 3789
    Prev
    Next
    INDEX
    Explanations

    starts sentences with personal pronouns

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

    The neuron activates on personal names in salutations (e.g. “Dear Marissa,” “Hi Cheryl,”).

    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
     greener
    0.67
     eigenstates
    0.59
    ítható
    0.59
     cooldown
    0.57
    ？
    0.57
    addGap
    0.56
    หรือไม่
    0.56
     trucker
    0.55
     distX
    0.55
     toppings
    0.55
    POSITIVE LOGITS
     Dieser
    0.75
     Regarding
    0.74
     Diese
    0.73
     👋
    0.73
    cm
    0.72
    Greetings
    0.70
     இதனை
    0.69
    رد
    0.68
     Whenever
    0.68
    this
    0.67
    Activations Density 0.021%

    No Known Activations