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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70735
    Prev
    Next
    INDEX
    Explanations

    sports event outcomes

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

    The neuron activates strongly on sports‐reporting passages—especially detailed match or competition descriptions.

    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
    ,
    -1.36
     british
    -1.28
    Cevap
    -1.25
    jelaskan
    -1.25
     Республики
    -1.23
     Whilst
    -1.20
    Approx
    -1.20
     extérieures
    -1.19
     celý
    -1.14
     (
    -1.13
    POSITIVE LOGITS
     trama
    1.77
     their
    1.66
     considera
    1.34
     espada
    1.34
     ideia
    1.31
     deciso
    1.31
    𝘩
    1.30
     capas
    1.29
     circun
    1.29
     aplic
    1.29
    Activations Density 0.031%

    No Known Activations