© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111537
    Prev
    Next
    INDEX
    Explanations

    sports events and olympics

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

    The neuron fires on numeric tokens marking years (especially four-digit dates) in the context of sporting events.

    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
    }}}{\
    -1.55
    хи
    -1.46
     that
    -1.41
     cualquier
    -1.40
     because
    -1.34
     bef
    -1.30
    $.
    -1.28
    erweise
    -1.24
    没有什么
    -1.23
     gogh
    -1.22
    POSITIVE LOGITS
    ımda
    1.27
    ellipse
    1.27
     muros
    1.23
     sẽ
    1.23
    »).
    1.22
    明白了
    1.22
     külön
    1.20
    fileType
    1.20
    olved
    1.20
    Toujours
    1.20
    Activations Density 0.066%

    No Known Activations