© 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. 67132
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

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

    The neuron fires on block‐terminating code tokens—e.g. closing braces (`}`) and `break` 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_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
     tylko
    -0.96
     untersucht
    -0.92
     aşağı
    -0.86
     Ł
    -0.85
    INCREF
    -0.84
     телеви
    -0.84
     っ
    -0.84
     numai
    -0.82
     tonight
    -0.82
    csak
    -0.81
    POSITIVE LOGITS
     if
    1.92
     If
    1.41
     out
    1.15
     from
    1.03
     based
    1.00
     если
    0.98
     often
    0.94
    If
    0.93
    TabLayout
    0.91
     Based
    0.90
    Activations Density 0.001%

    No Known Activations