© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13278
    Prev
    Next
    INDEX
    Explanations

    key-value assignments

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

    The neuron is triggered by PHP associative‐array key/value syntax (array declarations, the "=>" operator, quoted keys, etc.).

    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
     çünkü
    -1.76
    btnLogin
    -1.52
    ֺ
    -1.46
     להם
    -1.45
    ALAN
    -1.43
     μας
    -1.42
     campeones
    -1.38
     jejich
    -1.38
    illir
    -1.35
     τὴν
    -1.35
    POSITIVE LOGITS
    .
    2.17
     which
    1.63
     that
    1.59
     If
    1.59
     When
    1.57
     hendak
    1.43
     Whenever
    1.43
     Perhaps
    1.41
     to
    1.38
     Sometimes
    1.38
    Activations Density 0.005%

    No Known Activations