© 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. 79871
    Prev
    Next
    INDEX
    Explanations

    words starting with "the"

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

    This neuron fires on sentence-initial articles (“The,” “A”) that introduce product feature or description sentences.

    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
     those
    -1.59
     others
    -1.47
     discussion
    -1.19
    ׳
    -1.16
    carus
    -1.15
     zrobić
    -1.14
    ulite
    -1.13
    ֶּ
    -1.11
    ridescent
    -1.11
     other
    -1.10
    POSITIVE LOGITS
     also
    1.30
     dessutom
    1.21
     nostre
    1.15
    钠
    1.15
     sexe
    1.14
    ׇ
    1.12
     τὴν
    1.09
     comte
    1.09
     Ꮎ
    1.06
     erreur
    1.05
    Activations Density 0.043%

    No Known Activations