© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7192
    Prev
    Next
    INDEX
    Explanations

    they often have

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

    The neuron detects occurrences of the pronoun “They” (especially at the start of a sentence), as used to introduce what a business or people “they” do or offer.

    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
    Imidazole
    0.78
    ヌ
    0.77
    TaskManager
    0.71
    Tareas
    0.71
    MSBuild
    0.71
    albumin
    0.70
    doctorId
    0.70
    エキス
    0.70
    TComponent
    0.69
    Trab
    0.69
    POSITIVE LOGITS
     rainforest
    0.72
     you
    0.66
     *
    0.66
     yra
    0.66
     offerings
    0.66
     sells
    0.66
     restrooms
    0.66
     formats
    0.65
     اینجا
    0.64
     bathrooms
    0.63
    Activations Density 0.036%

    No Known Activations