© 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. 31-GEMMASCOPE-2-RES-16K
    4. 8345
    Prev
    Next
    INDEX
    Explanations

    head lamp

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

    This neuron detects direct second-person address—words and phrases that speak to “you” (e.g. you, your, customize you).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    product descriptions in e-commerce listings, particularly specifications and technical details.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    e-commerce style product descriptions that directly address the buyer while listing features, specifications, materials, and benefits.

    oai_token-act-pair · gpt-5Triggered 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
      
    0.70
     sassy
    0.69
     :
    0.60
     男
    0.57
     轻
    0.57
     কথোপ
    0.57
     silky
    0.55
     मल्टी
    0.54
     .”
    0.54
     playroom
    0.54
    POSITIVE LOGITS
    を見て
    0.52
    隷
    0.52
     себе
    0.50
     wellknown
    0.50
     (=
    0.50
    เดิม
    0.50
    krit
    0.49
     socalled
    0.49
     autosomal
    0.48
    Zed
    0.48
    Activations Density 0.002%

    No Known Activations