© 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. 10-GEMMASCOPE-RES-131K
    7. 39788
    Prev
    Next
    INDEX
    Explanations

    scoring in minutes

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

    The neuron fires on words describing scoring events or advances in a sports game (e.g. “get on the board,” “scoring,” “runs,” “doubled the advantage,” etc.).

    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
     these
    -1.82
     this
    -1.54
     désormais
    -1.51
    these
    -1.49
     pantalón
    -1.45
    Catatan
    -1.38
     temáticas
    -1.37
    𖣔
    -1.36
    鉭
    -1.34
    Kesimpulan
    -1.32
    POSITIVE LOGITS
    '
    1.77
     had
    1.49
     are
    1.48
     \
    1.44
    res
    1.41
     of
    1.41
    O
    1.41
     was
    1.41
    S
    1.34
    al
    1.30
    Activations Density 0.007%

    No Known Activations