© 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. 43241
    Prev
    Next
    INDEX
    Explanations

    questions beginning with auxiliary verbs

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

    The neuron fires strongly on sentence- (or clause-) initial function words—especially pronouns, articles, demonstratives, and conjunctions that start a new sentence or clause.

    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
     Sovi
    -1.79
     Luar
    -1.75
    商品説明
    -1.66
     kebaya
    -1.63
    These
    -1.62
     Reverso
    -1.61
    ाइल
    -1.59
     PÅ
    -1.59
     筆
    -1.59
     概要
    -1.56
    POSITIVE LOGITS
     the
    3.38
     
    2.19
     And
    2.06
     mencionado
    1.98
     your
    1.88
     it
    1.84
     harika
    1.80
     genellikle
    1.70
     vinculados
    1.70
    from
    1.66
    Activations Density 0.004%

    No Known Activations