© 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. 63968
    Prev
    Next
    INDEX
    Explanations

    pilot studies, programs, or projects

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

    The neuron consistently lights up on occurrences of the word “pilot” (whether referring to TV pilot season, test studies, aircraft pilots, pilot programs, etc.).

    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
     gesamten
    -1.03
     täglichen
    -0.86
    <strong>
    -0.85
     Vermögen
    -0.84
     wciąż
    -0.83
     liefern
    -0.81
     vierten
    -0.80
    <em>
    -0.79
     unteren
    -0.77
     faisant
    -0.77
    POSITIVE LOGITS
     program
    1.16
     whales
    1.05
    studie
    1.00
    projekt
    1.00
     esmalte
    0.99
    鮠
    0.98
     tabel
    0.97
     study
    0.96
    program
    0.95
     studies
    0.93
    Activations Density 0.012%

    No Known Activations