© 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. 28269
    Prev
    Next
    INDEX
    Explanations

    verbs followed by participles or 'to be'

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

    The neuron fires on the copular verb “is” (third‐person singular present tense) linking a subject to its complement.

    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
    to
    -1.55
    a
    -1.52
    O
    -1.49
    E
    -1.48
    e
    -1.48
    To
    -1.48
    '
    -1.48
    when
    -1.46
    P
    -1.45
    A
    -1.43
    POSITIVE LOGITS
     llavero
    1.82
     ſec
    1.64
     actualiza
    1.59
    鶺
    1.58
     araña
    1.58
    のデザイン
    1.57
    pendentif
    1.56
    mujer
    1.55
     negocia
    1.54
     sorteo
    1.53
    Activations Density 0.110%

    No Known Activations