© 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. 60574
    Prev
    Next
    INDEX
    Explanations

    becomes independent, binding, large

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

    The neuron fires on the main copular verbs (“is,” “becomes,” “just,” etc.) that introduce a formal result or definition in technical/math statements.

    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
    visning
    -1.80
    atical
    -1.63
    Ventajas
    -1.62
    IndentedString
    -1.55
     HttpNotFound
    -1.55
    atized
    -1.55
    cić
    -1.54
     {$\
    -1.54
    嗗
    -1.52
    ケモン
    -1.52
    POSITIVE LOGITS
    :
    2.27
    ↵
    2.02
    ”
    1.88
     like
    1.88
     if
    1.80
    '
    1.75
    ’
    1.60
    (
    1.59
     what
    1.56
    >
    1.56
    Activations Density 0.020%

    No Known Activations