© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 53815
    Prev
    Next
    INDEX
    Explanations

    X-UA-Compatible, edge

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

    This neuron strongly activates on the token “IE” (as in the X-UA-Compatible meta tag specifying Internet Explorer).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kufanya
    -0.70
     Hipp
    -0.68
     bütün
    -0.66
    ίκη
    -0.66
    宠物
    -0.65
    Rhythm
    -0.65
     dikel
    -0.64
    Ban
    -0.64
     belong
    -0.63
     ổ
    -0.63
    POSITIVE LOGITS
     primiti
    0.73
     orgasm
    0.72
    Obras
    0.72
     Hawley
    0.71
    mancy
    0.68
     lom
    0.65
    íny
    0.64
     roti
    0.64
    込めて
    0.63
     cuc
    0.63
    Activations Density 0.146%

    No Known Activations