© 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. 8797
    Prev
    Next
    INDEX
    Explanations

    company or organization names

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

    The neuron primarily detects named entities—proper nouns such as brand, company, or organization 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
    don
    0.62
    들에
    0.59
    들과
    0.58
    fourth
    0.57
    bildung
    0.55
    들도
    0.55
    等
    0.55
    Cal
    0.55
    संख्या
    0.55
    eighth
    0.55
    POSITIVE LOGITS
     GmbH
    0.97
     Corporation
    0.80
    ®.
    0.80
    ®
    0.79
     Ltd
    0.78
     CORPORATION
    0.78
     Bhd
    0.77
     spp
    0.73
     Sdn
    0.73
     ltd
    0.72
    Activations Density 0.285%

    No Known Activations