© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58579
    Prev
    Next
    INDEX
    Explanations

    date and time formatting

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

    This neuron activates on programming‐related tokens (library or API names, function calls, punctuation, and numeric literals) in code snippets.

    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
    ABUL
    -0.84
    álise
    -0.82
     Werkzeug
    -0.80
    mC
    -0.80
     LoginPage
    -0.80
     Toggle
    -0.79
     silber
    -0.79
    PERIOD
    -0.79
     kopf
    -0.78
    minder
    -0.77
    POSITIVE LOGITS
    format
    1.10
     format
    1.02
     add
    0.92
    add
    0.91
    Format
    0.90
    valueOf
    0.89
    WithFormat
    0.88
     Format
    0.86
     to
    0.75
     clone
    0.73
    Activations Density 0.004%

    No Known Activations