© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44608
    Prev
    Next
    INDEX
    Explanations

    awards and player honors

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

    The neuron detects mentions of named awards or honors (e.g. MVP, Cy Young, Jack Adams, Caldecott).

    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
     ellos
    -1.38
    /
    -1.36
     altres
    -1.36
     disappro
    -1.33
    TLDR
    -1.32
     ή
    -1.32
    </i>
    -1.31
    𝕠
    -1.30
    ()){
    -1.29
     Під
    -1.29
    POSITIVE LOGITS
     respekt
    1.44
     muerta
    1.35
    なのですが
    1.34
    喈
    1.34
    هور
    1.33
     veranderen
    1.30
     inmiddels
    1.30
     своё
    1.29
     verbinding
    1.27
     découvre
    1.27
    Activations Density 0.019%

    No Known Activations