© 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. 1381
    Prev
    Next
    INDEX
    Explanations

    company suffixes

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

    The neuron activates on tokens that are part of multiword proper names or branded titles—that is, it spots named‐entity tokens (brand, product, 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_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
    周囲
    0.49
    María
    0.46
    箇
    0.46
    瀟
    0.45
     آپ
    0.45
    toLocale
    0.44
    ခြေ
    0.44
    Укра
    0.44
    &&\
    0.43
    Geschichte
    0.43
    POSITIVE LOGITS
     Ltd
    0.75
     GmbH
    0.70
     ltd
    0.68
     LTD
    0.59
     llc
    0.58
     selaku
    0.58
     sangat
    0.57
     Sdn
    0.56
     adalah
    0.55
     LLC
    0.54
    Activations Density 0.185%

    No Known Activations