© 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. 9423
    Prev
    Next
    INDEX
    Explanations

    pianochrome, tan lines, Alan Turing

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

    The neuron fires on isolated proper names (particularly surnames or last names) in lists of authors or contributors.

    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
    ीय
    0.67
    ں
    0.66
    滞
    0.61
    ીએ
    0.59
    Inform
    0.58
    smöglichkeiten
    0.58
    ભાવ
    0.57
    nicht
    0.57
     ύ
    0.57
    guas
    0.57
    POSITIVE LOGITS
    larda
    0.83
    lardan
    0.80
    umeric
    0.77
    ব্ব
    0.75
    hattan
    0.74
    egra
    0.74
    cho
    0.73
    ews
    0.73
    ्ड
    0.72
     않으면
    0.71
    Activations Density 0.977%

    No Known Activations