© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38960
    Prev
    Next
    INDEX
    Explanations

    describing entities

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

    The neuron fires on the copula “are” when it’s immediately followed by a numeric value.

    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
    葙
    -1.88
     används
    -1.86
     ดู
    -1.75
    wendige
    -1.75
     ieder
    -1.72
    ↵↵
    -1.70
    clicking
    -1.69
    indicated
    -1.68
    provides
    -1.67
     vegano
    -1.67
    POSITIVE LOGITS
     that
    2.13
     from
    2.06
     without
    1.83
     to
    1.82
     grudnia
    1.81
     with
    1.81
     on
    1.75
     Of
    1.71
     cleverly
    1.67
     wrze
    1.66
    Activations Density 0.030%

    No Known Activations