© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80723
    Prev
    Next
    INDEX
    Explanations

    image file operations

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

    The neuron identifies programming‐language tokens, in particular Java/Android code elements (e.g. braces, class/method names, variable assignments).

    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
     meisjes
    -0.75
     камер
    -0.72
    CompoundButton
    -0.71
    ulario
    -0.71
    èvent
    -0.70
    entiation
    -0.69
    繊
    -0.69
    ADUATE
    -0.69
    πο
    -0.69
    Legende
    -0.69
    POSITIVE LOGITS
    ARGB
    0.94
    IsMutable
    0.87
    setImageBitmap
    0.86
    libat
    0.85
     Bitmap
    0.81
     бит
    0.81
    Bitmap
    0.80
     density
    0.79
     Kleid
    0.78
     punch
    0.77
    Activations Density 0.007%

    No Known Activations