© 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. 113048
    Prev
    Next
    INDEX
    Explanations

    team performance and actions

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

    The neuron fires on tokens referring to a sports team or its roster (e.g. “team,” “squad,” “players,” “signed”).

    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
     --
    -1.45
     /
    -1.41
     must
    -1.37
    llten
    -1.36
     Within
    -1.33
     if
    -1.31
     применя
    -1.31
    们
    -1.27
    A
    -1.26
    If
    -1.25
    POSITIVE LOGITS
    していますが
    1.57
     aislada
    1.55
    fucking
    1.51
     femeninos
    1.48
     destinados
    1.46
    ⢊
    1.45
    (‘
    1.43
    そうですが
    1.41
     almacenar
    1.40
     wey
    1.40
    Activations Density 0.027%

    No Known Activations