© 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. 8006
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on words denoting positive action or assistance—verbs that express serving, helping, supporting, or otherwise benefiting others.

    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
    一些
    0.82
     threes
    0.71
    dört
    0.71
     వచ్చిన
    0.70
    ڵ
    0.70
    ടുത്ത
    0.68
    髅
    0.68
    CO
    0.68
    드는
    0.68
     itinéraires
    0.68
    POSITIVE LOGITS
    ตัวเอง
    1.27
     собой
    1.20
    ตน
    1.00
     sobą
    1.00
     humanity
    0.97
     себя
    0.96
     Shareholders
    0.95
     humankind
    0.94
     shareholders
    0.93
     தன்னை
    0.93
    Activations Density 2.167%

    No Known Activations