© 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. 129220
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on award mentions that start with the word “Best,” i.e. phrases naming “Best” awards.

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

    best awards categories

    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
    opie
    -1.42
     magnific
    -1.41
    zzet
    -1.38
    eſ
    -1.38
    栊
    -1.37
     hebben
    -1.36
     famoso
    -1.34
     предотвра
    -1.34
    ḿ
    -1.34
     dando
    -1.32
    POSITIVE LOGITS
     all
    2.11
     using
    1.86
     in
    1.84
     having
    1.70
     such
    1.65
     like
    1.62
    Although
    1.58
    During
    1.57
     not
    1.56
     under
    1.56
    Activations Density 0.020%

    No Known Activations