© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128503
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on specific proper nouns—especially brand names, place names, product names, and other named entities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    specific entities and their continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     veno
    -0.89
    vidia
    -0.88
     Traducción
    -0.85
     เก
    -0.84
     وكان
    -0.84
    chtend
    -0.84
     Româ
    -0.82
    TypeService
    -0.82
     nochmal
    -0.82
     naszego
    -0.82
    POSITIVE LOGITS
     وغير
    2.48
     or
    2.48
    和其他
    2.38
    乃至
    1.41
     etc
    1.33
     among
    1.27
    をはじめ
    1.26
    以及
    1.21
     along
    1.19
     and
    1.13
    Activations Density 0.293%

    No Known Activations