© 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. 22-GEMMASCOPE-RES-131K
    7. 73411
    Prev
    Next
    INDEX
    Explanations

    baseball hitting terms

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

    The neuron detects mentions of specific sports-play action phrases (e.g. multiword terms naming particular plays).

    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
    áneas
    -1.03
    Lastly
    -1.03
    謦
    -1.02
    Տես
    -1.02
    tyfik
    -1.00
    tividad
    -0.92
     seules
    -0.91
    已是
    -0.91
    mRNA
    -0.91
     этих
    -0.91
    POSITIVE LOGITS
     while
    1.16
    hø
    1.01
     when
    1.00
    téri
    0.98
    ୟ
    0.96
     caused
    0.94
     but
    0.93
    payers
    0.93
     causing
    0.92
    autoconfigure
    0.92
    Activations Density 0.003%

    No Known Activations