© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105399
    Prev
    Next
    INDEX
    Explanations

    common verbs followed by descriptive words

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

    The neuron strongly activates on common grammatical function words—especially forms of the verb “to be” (is, are, were, will be/provided) and similar high-frequency pronouns like “we.”

    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
    áže
    -1.30
     techni
    -1.29
    lides
    -1.27
     Laufe
    -1.24
     жители
    -1.23
     surpris
    -1.19
    毙
    -1.17
     ij
    -1.16
     vack
    -1.16
     are
    -1.16
    POSITIVE LOGITS
     various
    1.49
     increases
    1.36
     wzglę
    1.31
     using
    1.31
     иногда
    1.30
     różnych
    1.30
     brings
    1.26
     increasing
    1.21
     HUGE
    1.20
     different
    1.19
    Activations Density 0.268%

    No Known Activations