© 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. 60866
    Prev
    Next
    INDEX
    Explanations

    core animation layers and animations

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

    This neuron identifies programming code snippets, i.e. sequences of source‐code tokens and syntax.

    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
    ENDS
    -0.71
    UJ
    -0.69
     alg
    -0.69
    setupUi
    -0.68
    #$
    -0.68
    atoga
    -0.68
     veloce
    -0.66
    phol
    -0.66
    glise
    -0.66
     Mong
    -0.66
    POSITIVE LOGITS
     layer
    1.09
     CAL
    1.01
     CALIF
    0.94
     CAS
    0.85
    Layer
    0.83
     layers
    0.82
     paused
    0.82
    layer
    0.82
    Dye
    0.79
     californ
    0.78
    Activations Density 0.041%

    No Known Activations