© 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. 35871
    Prev
    Next
    INDEX
    Explanations

    for a/an

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

    The neuron strongly activates on 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
     procedimentos
    -1.27
     kei
    -1.16
     puisque
    -1.09
     benefícios
    -1.09
     makro
    -1.08
     rokok
    -1.06
     neón
    -1.05
     aki
    -1.05
     eil
    -1.05
     keram
    -1.04
    POSITIVE LOGITS
    We
    1.23
     as
    1.11
    Aren
    1.09
    Yet
    1.09
    Doesn
    1.08
    ]$.
    1.05
    And
    1.05
    ),
    1.03
    henden
    1.01
    as
    1.00
    Activations Density 0.067%

    No Known Activations