© 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. 11505
    Prev
    Next
    INDEX
    Explanations

    unst, -un- words

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

    The neuron strongly activates on personal names—especially surnames—in lists of authors or 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
    ристо
    0.65
    ド
    0.61
    asad
    0.60
    gente
    0.59
    د
    0.59
    雙
    0.59
    𝐎
    0.59
    𝗢
    0.58
    ilä
    0.57
    ेल
    0.57
    POSITIVE LOGITS
    nen
    0.75
    ni
    0.72
    nes
    0.69
    nies
    0.69
    ktion
    0.68
    nie
    0.68
    ąć
    0.67
    ners
    0.67
    nel
    0.67
    nings
    0.66
    Activations Density 0.570%

    No Known Activations