© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3564
    Prev
    Next
    INDEX
    Explanations

    Microsoft products and services

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

    The neuron responds to mentions of prominent brand or company names (e.g. HP, Sony, Canon, Ford, Dell, Amazon).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    чему
    0.45
    珉
    0.44
     करोड़
    0.43
     কেহ
    0.42
     президента
    0.40
    ちょっと
    0.40
     باست
    0.40
    acrylamide
    0.40
    Could
    0.39
    oky
    0.39
    POSITIVE LOGITS
    ®
    0.51
     UK
    0.46
     dealerships
    0.44
     woke
    0.42
     originals
    0.42
     Originals
    0.41
     bombé
    0.41
     serii
    0.41
     aficionados
    0.41
     eBooks
    0.40
    Activations Density 0.322%

    No Known Activations