© 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. 12404
    Prev
    Next
    INDEX
    Explanations

    proud to be

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

    The neuron detects occurrences of the verb “be” (in its various forms such as “be,” “being,” “are,” etc.).

    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
     or
    -2.36
     if
    -1.83
     other
    -1.69
     on
    -1.68
     for
    -1.58
     I
    -1.43
     like
    -1.41
     in
    -1.36
     an
    -1.36
     as
    -1.34
    POSITIVE LOGITS
     armada
    1.48
    鴬
    1.48
    ésultats
    1.47
     legendar
    1.47
     indepen
    1.45
     rezult
    1.43
    भग
    1.43
     epide
    1.41
    </b>
    1.39
     canel
    1.38
    Activations Density 0.024%

    No Known Activations