© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79896
    Prev
    Next
    INDEX
    Explanations

    countries and associated topics

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

    The neuron fires on isolated single-letter “a” tokens (the indefinite article “a”).

    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
     on
    -1.05
     what
    -0.99
     they
    -0.96
     you
    -0.96
     conventional
    -0.95
     valamint
    -0.94
     in
    -0.94
     those
    -0.93
     of
    -0.93
    なりに
    -0.92
    POSITIVE LOGITS
     néanmoins
    1.23
    </em>
    1.13
    Nevertheless
    1.12
    还是很
    1.04
     quia
    1.02
     herausgegeben
    1.02
    Seeing
    1.02
    却是
    1.01
    בוצ
    0.96
    Nonetheless
    0.96
    Activations Density 0.000%

    No Known Activations