© 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. 118894
    Prev
    Next
    INDEX
    Explanations

    wiki/

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

    The neuron activates on the “wiki” part of Wikipedia URLs (i.e. the “/wiki/…” path segment).

    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
     in
    -2.86
     can
    -2.16
     have
    -2.14
     ,
    -2.14
    );
    -2.09
     by
    -2.06
     with
    -2.00
     as
    -2.00
    ;
    -2.00
     from
    -1.97
    POSITIVE LOGITS
     diki
    2.31
    냑
    2.23
     délais
    2.22
    ㈮
    2.17
     soucis
    2.17
     hırka
    2.13
     ekonomi
    2.02
    ementara
    1.99
     patienter
    1.98
    塒
    1.95
    Activations Density 0.001%

    No Known Activations