© 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. 22-GEMMASCOPE-RES-131K
    7. 38464
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or delimiters

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

    The neuron fires primarily on semicolons (the end‐of‐statement marker) in code.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    KN
    -0.93
     Then
    -0.86
     scrutin
    -0.84
    itt
    -0.83
    return
    -0.82
     WELFARE
    -0.82
     Things
    -0.81
    LatLng
    -0.81
    KC
    -0.79
    她也
    -0.78
    POSITIVE LOGITS
     rengi
    0.95
    Déf
    0.93
    Arquivo
    0.91
     öz
    0.89
    Among
    0.88
     pelindung
    0.88
     consists
    0.87
     sendok
    0.86
     punggung
    0.86
     ellos
    0.85
    Activations Density 0.035%

    No Known Activations