© 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. 10-GEMMASCOPE-RES-131K
    7. 23942
    Prev
    Next
    INDEX
    Explanations

    media URLs with @username

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

    The neuron is primarily detecting links to Medium articles (appearances of “medium.com” in URLs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ཫ
    -1.79
     them
    -1.66
     mariposas
    -1.53
    wieś
    -1.51
    ໊
    -1.48
     "@/
    -1.48
    selben
    -1.46
    ながら
    -1.45
     últimas
    -1.44
    SenderId
    -1.44
    POSITIVE LOGITS
    在
    1.84
    ar
    1.83
    \
    1.59
    s
    1.52
     frites
    1.52
    let
    1.50
    菒
    1.49
    to
    1.45
    ب
    1.45
    go
    1.44
    Activations Density 0.008%

    No Known Activations