© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42918
    Prev
    Next
    INDEX
    Explanations

    track and field

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

    The neuron responds whenever it sees the word "track" (in any context).

    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
            
    -3.33
    *
    -2.33
    훙
    -2.31
    </strong>
    -2.28
    書いた
    -2.27
                
    -2.17
    ."
    -2.17
    鹮
    -2.16
    FWIW
    -2.14
         
    -2.11
    POSITIVE LOGITS
     všetkých
    2.86
     utilise
    2.75
     uncover
    2.67
    ll
    2.66
    斗争
    2.66
     poži
    2.64
     THEIR
    2.63
     zijn
    2.61
     thier
    2.61
     tisíc
    2.59
    Activations Density 0.021%

    No Known Activations