© 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. 10-GEMMASCOPE-RES-131K
    4. 11498
    Prev
    Next
    INDEX
    Explanations

    uploading files

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

    the word "upload" in code and technical documentation contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The main thing this neuron does is detect the word “upload” (in any context or language variant).

    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
    >
    -3.38
    ",
    -3.13
    2
    -3.09
    st
    -3.05
    *
    -3.03
    [
    -3.00
    /
    -3.00
    T
    -2.97
    R
    -2.97
    B
    -2.95
    POSITIVE LOGITS
    〼
    2.98
    珖
    2.98
    瑒
    2.92
     proveedores
    2.83
    ケモン
    2.83
     compradores
    2.81
    
    2.80
    ﻊ
    2.78
     conductores
    2.64
     ingenieros
    2.58
    Activations Density 0.007%

    No Known Activations