© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14170
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns related to sports transfers

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

    The neuron strongly activates on football-related proper names—particularly club and player names (often in headlines or possessive ’s constructions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     aboli
    -1.27
     its
    -1.22
     CONSE
    -1.20
     capot
    -1.15
     carteira
    -1.15
     ASSETS
    -1.09
     bricola
    -1.09
     umbro
    -1.09
     IMPLEMENT
    -1.08
     tava
    -1.08
    POSITIVE LOGITS
     únicamente
    0.95
     analisar
    0.94
    :
    0.93
    Considering
    0.92
     вот
    0.90
     &
    0.90
     dziś
    0.90
     cubierto
    0.89
     x
    0.89
    am
    0.88
    Activations Density 0.011%

    No Known Activations