© 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. 60343
    Prev
    Next
    INDEX
    Explanations

    Creative Commons and specific resources

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

    The neuron is triggered by URL mentions of “wiki” (e.g. wiki.org, wikimedia.org, openstreetmap.org) in the text.

    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
     läuft
    -0.80
     gewe
    -0.79
     dirinya
    -0.76
    imbo
    -0.74
     slides
    -0.73
     mathvariant
    -0.71
     сообщили
    -0.71
    𝙲
    -0.70
     olen
    -0.70
     ład
    -0.69
    POSITIVE LOGITS
     adesso
    0.86
     معلم
    0.84
     فنا
    0.83
    小小
    0.80
    掲載
    0.80
    onien
    0.80
    hängig
    0.79
    formazioni
    0.79
     fascic
    0.78
     SqlDbType
    0.77
    Activations Density 0.009%

    No Known Activations