© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64497
    Prev
    Next
    INDEX
    Explanations

    associated with parts or names

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

    The neuron consistently activates on instances of the copula “to be” (and its conjugated forms like “is,” “was,” “are,” “became,” etc.) in various contexts.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    REVISTA
    -0.80
    Ԁ
    -0.79
     stället
    -0.78
    Transk
    -0.75
     ไม่มี
    -0.74
    árqu
    -0.73
     pono
    -0.73
    小时候
    -0.72
    ることができる
    -0.71
    嚮
    -0.71
    POSITIVE LOGITS
    BIÉN
    0.85
     part
    0.83
    দ
    0.82
     heir
    0.82
     belongs
    0.81
     corre
    0.81
    artamento
    0.80
    ǚ
    0.79
     estamos
    0.79
    zné
    0.79
    Activations Density 0.059%

    No Known Activations