© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12328
    Prev
    Next
    INDEX
    Explanations

    Arabic and names starting with H/M

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

    The neuron detects occurrences of personal proper names.

    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
    chent
    0.68
     c
    0.57
    ंधर
    0.57
    che
    0.55
     kö
    0.54
     XML
    0.54
    ఘ
    0.54
     CO
    0.54
     vinden
    0.54
    CO
    0.54
    POSITIVE LOGITS
    افظ
    0.77
    ركات
    0.65
    فاظ
    0.64
    داث
    0.64
     அந்த
    0.62
    iguë
    0.59
    <unused2115>
    0.58
     thật
    0.57
    افة
    0.57
    wq
    0.57
    Activations Density 0.028%

    No Known Activations