© 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. 6977
    Prev
    Next
    INDEX
    Explanations

    furnished to do

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

    The neuron is specialized to pick out the Go “sync” package (and related sync‐based identifiers) in code.

    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
     Cornelia
    -0.81
     columbia
    -0.66
     Lul
    -0.65
    谧
    -0.65
    gten
    -0.64
    タン
    -0.63
    それぞれの
    -0.63
     Moun
    -0.62
     Schenectady
    -0.62
     Sophomore
    -0.61
    POSITIVE LOGITS
     mye
    0.80
     selv
    0.75
    angaben
    0.74
     memutuskan
    0.72
    bited
    0.70
     ilk
    0.70
    phal
    0.70
    Released
    0.69
    watched
    0.69
    
    0.69
    Activations Density 0.050%

    No Known Activations