© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102891
    Prev
    Next
    INDEX
    Explanations

    assemble and put together

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

    The neuron flags mentions of putting things together or reassembling—i.e. words and forms related to assembly (assemble, assembled, assembly, assemblies, together).

    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
    5
    -2.06
     to
    -1.73
     
    -1.70
    b
    -1.51
    9
    -1.48
     if
    -1.48
     try
    -1.43
    3
    -1.41
     we
    -1.38
    8
    -1.38
    POSITIVE LOGITS
    歃
    1.84
     a
    1.59
     our
    1.57
    棪
    1.52
     maquillage
    1.51
     fallu
    1.50
    ⛧
    1.49
     roupa
    1.49
    imize
    1.46
     capuche
    1.43
    Activations Density 0.047%

    No Known Activations