© 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. 10-GEMMASCOPE-RES-131K
    7. 19136
    Prev
    Next
    INDEX
    Explanations

    words indicating being or auxiliary verbs

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

    The neuron activates on auxiliary or copular verb forms (e.g. is/was/are, did, had and their equivalents in other languages).

    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
    this
    -2.67
     was
    -2.45
    \
    -2.30
    на
    -2.28
     of
    -2.00
    <()>
    -1.93
    the
    -1.88
    This
    -1.88
    such
    -1.84
    scaleY
    -1.81
    POSITIVE LOGITS
     nisso
    2.13
    ⸫
    2.08
     flesta
    1.90
     bénéficiaire
    1.86
    Hilsen
    1.86
     ſen
    1.83
     houver
    1.82
    Créditos
    1.81
    idk
    1.79
     intentó
    1.78
    Activations Density 0.002%

    No Known Activations