© 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. 1977
    Prev
    Next
    INDEX
    Explanations

    The neuron is picking out proper names and named‐entity tokens (e.g. people, organizations, brands, acronyms).

    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
    тив
    0.59
     μέ
    0.59
    주
    0.54
     inoltre
    0.54
    ⑵
    0.53
    five
    0.53
     trụ
    0.52
    법
    0.52
     стра
    0.52
    yez
    0.52
    POSITIVE LOGITS
    ہرست
    0.78
    riends
    0.75
    aktor
    0.73
    ácil
    0.68
    lections
    0.66
    actoring
    0.66
    Paf
    0.65
    ્
    0.65
    iciency
    0.64
    avourite
    0.64
    Activations Density 0.726%

    No Known Activations