© 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. 7298
    Prev
    Next
    INDEX
    Explanations

    names in texts

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

    This neuron detects personal names (proper nouns referring to people).

    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
    মিও
    0.62
    ទទួលបាន
    0.61
    욥
    0.59
    डून
    0.59
     получила
    0.59
     नाराजगी
    0.58
    女優
    0.57
    interpre
    0.57
     absolutamente
    0.57
    និយាយ
    0.55
    POSITIVE LOGITS
    ؔ
    0.99
     यांच्या
    0.88
     aka
    0.87
     ওরফে
    0.86
     उर्फ
    0.79
     (~
    0.78
     Esq
    0.77
     (
    0.76
     ($
    0.76
     (“
    0.75
    Activations Density 0.170%

    No Known Activations