© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15788
    Prev
    Next
    INDEX
    Explanations

    EMIEW2 uses wheels

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

    The neuron fires strongly on detailed product‐specification and feature‐description language (e.g. technical equipment and comfort amenity terms).

    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
     ragazza
    0.63
     बिहार
    0.61
     negras
    0.59
     الرخصة
    0.57
     foreign
    0.56
    秏
    0.56
    齊
    0.55
     meninas
    0.55
     مدينه
    0.55
     دختر
    0.54
    POSITIVE LOGITS
    惬
    0.71
    optional
    0.69
     optional
    0.67
    Optional
    0.64
     optionally
    0.63
    扰
    0.63
    ătur
    0.62
    kWh
    0.61
     bolstering
    0.61
     Optionally
    0.61
    Activations Density 0.242%

    No Known Activations