© 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. 31-GEMMASCOPE-2-RES-16K
    7. 786
    Prev
    Next
    INDEX
    Explanations

    impressive sensations or qualities

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

    The neuron is sensitive to proper nouns and named entities—brand names, drug names, place names, organization names, etc.

    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_31_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
    ATT
    0.46
    
    0.45
    경
    0.43
     <!--
    0.43
    永远
    0.42
    ComponentName
    0.42
     ใช่
    0.41
     подчи
    0.41
     กรณี
    0.41
     แอ
    0.41
    POSITIVE LOGITS
    ície
    0.51
    been
    0.50
     ofthe
    0.50
    <start_of_image>
    0.48
     ہیں۔
    0.47
    ‌.
    0.46
     shutterstock
    0.46
     tambien
    0.46
     been
    0.45
     myös
    0.45
    Activations Density 0.254%

    No Known Activations