© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60631
    Prev
    Next
    INDEX
    Explanations

    C# get properties

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

    The neuron is strongly activated by code‐style punctuation and delimiting symbols (e.g. semicolons, parentheses, braces) that mark statement and block boundaries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     کفش
    -0.78
    armée
    -0.77
     takımı
    -0.77
    국의
    -0.75
     takım
    -0.74
    男主
    -0.74
    reflect
    -0.73
    tiff
    -0.73
    ddots
    -0.70
    hláš
    -0.68
    POSITIVE LOGITS
     fields
    1.07
    Field
    1.04
     MethodInfo
    0.99
    Method
    0.98
     Binding
    0.94
    Fields
    0.93
     Fields
    0.92
    Property
    0.91
    Binding
    0.91
     field
    0.90
    Activations Density 0.007%

    No Known Activations