© 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. 10-GEMMASCOPE-RES-131K
    7. 86454
    Prev
    Next
    INDEX
    Explanations

    a/an followed by descriptive adjectives

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

    This neuron fires on indefinite-article noun phrases—especially “a” or “an” plus descriptive adjectives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     our
    -2.16
     patienter
    -1.87
    Продам
    -1.85
     annons
    -1.84
     désolés
    -1.80
    獃
    -1.76
    
    -1.73
    鱻
    -1.71
    Berikut
    -1.68
     épo
    -1.65
    POSITIVE LOGITS
     for
    2.16
     and
    2.13
     
    2.08
     ability
    1.90
     .
    1.40
     permits
    1.38
     desire
    1.36
    <blockquote>
    1.30
    riterion
    1.30
     in
    1.29
    Activations Density 0.064%

    No Known Activations