© 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. 34-GEMMASCOPE-RES-131K
    7. 57198
    Prev
    Next
    INDEX
    Explanations

    science centers and museums

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

    This neuron fires on mentions of “Science Center” (and related institutional names like science museums/planetariums).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
      
    -0.74
    TokenNameDOT
    -0.74
    ymal
    -0.74
    QQ
    -0.72
    clusive
    -0.72
     obrigado
    -0.71
     monumental
    -0.71
    комиться
    -0.71
    ñez
    -0.70
     PERFORMANCE
    -0.70
    POSITIVE LOGITS
     planet
    1.26
     Science
    1.15
     museum
    1.13
     IMAX
    1.13
     science
    1.11
     dome
    1.10
     STEM
    1.05
     exhibits
    0.98
    Science
    0.97
    museum
    0.89
    Activations Density 0.018%

    No Known Activations