© 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. 1446
    Prev
    Next
    INDEX
    Explanations

    Mit/Mid prefixes

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

    The neuron chiefly responds to personal names (proper nouns identifying 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
     dotted
    0.55
    innan
    0.55
     ਜ਼
    0.52
    SECUR
    0.52
     veiled
    0.50
    SEQU
    0.49
     حوالے
    0.48
    ^{[
    0.48
    ISSU
    0.48
    _{
    0.47
    POSITIVE LOGITS
     мі
    0.96
     ミ
    0.88
     Ми
    0.88
     مي
    0.83
    hael
    0.83
    ミ
    0.81
    Ми
    0.80
     Mi
    0.78
     mip
    0.77
    মি
    0.76
    Activations Density 0.344%

    No Known Activations