© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1985
    Prev
    Next
    INDEX
    Explanations

    "vot ona"

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

    This neuron detects capitalized proper names (i.e. person names) in the text.

    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
    зге
    0.78
     perin
    0.69
     personalizados
    0.68
     निष्
    0.67
    ان
    0.66
    ﺔ
    0.66
     انتخاب
    0.66
    бычно
    0.65
    蘋
    0.65
    ปัจ
    0.64
    POSITIVE LOGITS
    olazione
    0.88
    nione
    0.83
     Inoltre
    0.79
     ہے۔
    0.77
     Questa
    0.76
     -
    0.75
     અધિક
    0.75
     Dette
    0.74
    onerror
    0.74
     Cancell
    0.73
    Activations Density 0.005%

    No Known Activations