© 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. 60152
    Prev
    Next
    INDEX
    Explanations

    URLs and data fetching

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

    The neuron is keying on promise‐style `.then(` chains in code (i.e. the “then(” in async promise handlers).

    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
    Ayuda
    -0.72
    ENE
    -0.71
     てい
    -0.70
     Agrawal
    -0.69
    SendMessage
    -0.68
    ={`
    -0.68
    ascin
    -0.68
    יס
    -0.68
    tolist
    -0.66
    (({
    -0.66
    POSITIVE LOGITS
    Blood
    0.69
    нато
    0.68
    pler
    0.68
     Washing
    0.66
     response
    0.66
    ulz
    0.65
    neiden
    0.65
    묵
    0.64
     لعب
    0.64
    𝑃
    0.63
    Activations Density 0.062%

    No Known Activations