© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10675
    Prev
    Next
    INDEX
    Explanations

    facets, facilitates

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

    The neuron activates on proper‐noun or named‐entity tokens (e.g. personal names, brands, titles, and other capitalized entities).

    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
    Checkout
    0.59
     fonte
    0.58
     connus
    0.57
    isien
    0.57
     hipot
    0.56
    Altitude
    0.56
    衹
    0.56
    ăm
    0.55
     fuertes
    0.54
    Compliance
    0.54
    POSITIVE LOGITS
     Фа
    1.09
     фа
    0.82
     Fac
    0.82
     FA
    0.79
     Fa
    0.79
    Фа
    0.77
     Fasc
    0.72
     approximate
    0.70
     فا
    0.67
     Fas
    0.67
    Activations Density 0.326%

    No Known Activations