© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111493
    Prev
    Next
    INDEX
    Explanations

    Nelumbo, Nelvana, nelsoni

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

    The neuron is looking for module exports in JavaScript code or proper names starting with "Nel" across various texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on occurrences of the “__esModule” identifier (the __esModule export flag in compiled JS modules).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     verschill
    -2.39
    弍
    -2.34
    .
    -2.30
    
    -2.25
    媗
    -2.20
    šiť
    -2.11
    はその
    -2.09
     ecuator
    -2.05
    是想
    -2.03
     bijzonder
    -2.02
    POSITIVE LOGITS
     Architekt
    2.11
    ⇴
    2.05
    ских
    1.97
    よかった
    1.91
    [
    1.85
    0
    1.83
     credere
    1.82
    躄
    1.81
    家居
    1.79
    絰
    1.78
    Activations Density 0.001%

    No Known Activations