© 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. 11304
    Prev
    Next
    INDEX
    Explanations

    names and surnames

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

    The neuron strongly activates on proper names and other named-entity tokens (e.g. people’s surnames, place names, organization names).

    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
     fragmentary
    0.63
    
    0.63
     induc
    0.63
    ほどの
    0.59
    gekehrt
    0.59
    สบาย
    0.59
    繋がりたい
    0.58
     vegetative
    0.57
     फर्निश्ड
    0.57
    ),]),
    0.57
    POSITIVE LOGITS
     brothers
    0.86
     family
    0.84
    stown
    0.83
    ية
    0.77
    family
    0.76
     Family
    0.76
     clan
    0.74
     County
    0.73
     siblings
    0.73
    sville
    0.73
    Activations Density 0.511%

    No Known Activations