© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2970
    Prev
    Next
    INDEX
    Explanations

    toy, toys, toy-like, juguetes

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

    The neuron is spotting detailed e-commerce product listing language—especially toy or gift item names and their descriptive attributes.

    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
     prophylaxis
    0.63
     esophageal
    0.56
    ogène
    0.56
     புரி
    0.55
     outflows
    0.55
    othelium
    0.54
     ওয়ে
    0.53
    _{-}\
    0.53
    jno
    0.53
     anticoag
    0.53
    POSITIVE LOGITS
     toy
    2.22
     toys
    2.16
     Toys
    2.02
    玩具
    1.94
    Toys
    1.88
    toys
    1.86
     juguetes
    1.84
     juguete
    1.83
    toy
    1.80
     Toy
    1.74
    Activations Density 0.557%

    No Known Activations