© 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. 112508
    Prev
    Next
    INDEX
    Explanations

    sent packing

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

    The neuron specifically detects mentions of disciplinary ejections or punishments in sports (e.g., being sent off, red cards, bans).

    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
     centaines
    -1.70
    ﯼ
    -1.69
    咘
    -1.68
     blessures
    -1.67
     certainty
    -1.63
    袛
    -1.63
    ﮑ
    -1.59
     dieťa
    -1.59
     dizaines
    -1.57
    蕯
    -1.57
    POSITIVE LOGITS
     preclude
    1.40
     o
    1.38
    8
    1.37
    ed
    1.33
     двумя
    1.30
    9
    1.30
    gridx
    1.27
     delusions
    1.27
     after
    1.24
     使っ
    1.24
    Activations Density 0.003%

    No Known Activations