© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128005
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on code‐related identifier tokens—especially parts of URLs, file paths, and version numbers (i.e. strings containing digits or domain segments).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code structure or language syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     habang
    -0.93
    裝
    -0.90
    ładka
    -0.87
    :!
    -0.87
    ためには
    -0.86
     płyn
    -0.86
    Ｚ
    -0.86
    🤨
    -0.85
    喻
    -0.85
    ADDY
    -0.85
    POSITIVE LOGITS
    íba
    1.19
    omenclature
    1.11
    pantalones
    1.08
     Robbery
    1.08
    マッサージ
    1.07
    <0xA3>
    1.05
    があり
    1.02
     Nhưng
    1.01
     erwähnten
    1.00
    ticular
    0.99
    Activations Density 0.009%

    No Known Activations