© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107898
    Prev
    Next
    INDEX
    Explanations

    ILAsm, IL App, interleukin

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

    programming language and file format identifiers like "IL" (Intermediate Language) and language/library abbreviations.

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

    The neuron specifically detects the standalone token “IL.”

    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
     one
    -1.39
     every
    -1.27
     on
    -1.20
     until
    -1.18
     fifteen
    -1.16
     not
    -1.13
     all
    -1.13
     what
    -1.11
     new
    -1.10
     even
    -1.10
    POSITIVE LOGITS
     signif
    1.07
    cpp
    1.05
    commonly
    1.01
    奩
    1.01
    mainly
    1.00
     llor
    0.99
    
    0.98
     火锅
    0.96
     dieß
    0.96
     facil
    0.96
    Activations Density 0.002%

    No Known Activations