© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3236
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on personal names (proper names of individuals).

    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
    ترف
    0.43
    ൌ
    0.40
     സ്വന്ത
    0.40
     લગભગ
    0.40
     হেসে
    0.39
     baada
    0.39
     ممکن
    0.39
    Faces
    0.39
    衣裙
    0.39
    纪录
    0.38
    POSITIVE LOGITS
     who
    0.70
    -
    0.70
     Esq
    0.66
     our
    0.66
     aka
    0.66
     from
    0.64
     representing
    0.61
     their
    0.61
     Garcia
    0.59
     selaku
    0.59
    Activations Density 0.194%

    No Known Activations