© 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. 11869
    Prev
    Next
    INDEX
    Explanations

    The neuron is specifically triggered by occurrences of the proper name “Jimmy.”

    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
     ofthe
    0.72
    谪
    0.65
    據
    0.58
     setae
    0.58
    
    0.58
     всей
    0.56
     crumpled
    0.56
    имость
    0.56
    िश्च
    0.55
    क्षण
    0.55
    POSITIVE LOGITS
    으로부터
    0.61
     relacionados
    0.58
     trưng
    0.56
    )]$
    0.54
    ]$
    0.54
     συνα
    0.53
    களை
    0.52
     betreff
    0.52
    ))))
    0.51
    rasi
    0.51
    Activations Density 0.002%

    No Known Activations