© 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. 34-GEMMASCOPE-RES-131K
    7. 91888
    Prev
    Next
    INDEX
    Explanations

    a/an positive adjective

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

    This neuron detects the standalone 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_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
    few
    -1.13
    Kemudian
    -1.05
    Tetapi
    -1.05
    parently
    -1.04
     épices
    -0.99
    Sedangkan
    -0.96
     valgt
    -0.94
     membag
    -0.93
    Selanjutnya
    -0.93
     весьма
    -0.92
    POSITIVE LOGITS
     balanced
    1.33
     healthy
    1.32
     better
    1.25
     sustainable
    1.23
     strong
    1.17
     robust
    1.09
     healthier
    1.02
     comprehensive
    1.01
     successful
    1.00
     balance
    0.98
    Activations Density 0.074%

    No Known Activations