© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6728
    Prev
    Next
    INDEX
    Explanations

    Yi, Voisin, Pierson, hyun, anka

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

    The neuron fires strongly on 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_24_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
    J
    0.14
     L
    0.13
     T
    0.13
     J
    0.13
     A
    0.13
     त्यांना
    0.12
     F
    0.12
     G
    0.12
     cellules
    0.12
    L
    0.12
    POSITIVE LOGITS
    ຯ
    0.14
     buddhav
    0.14
    дации
    0.14
     jurispr
    0.14
    examtype
    0.13
     afresh
    0.13
    звание
    0.13
    lcnaf
    0.13
     دبستان
    0.13
    gende
    0.13
    Activations Density 0.000%

    No Known Activations