© 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. 10-GEMMASCOPE-RES-131K
    7. 69154
    Prev
    Next
    INDEX
    Explanations

    programming code, namespaces, exceptions

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

    This neuron fires on programming/code tokens—especially keywords and identifier names (e.g. namespace declarations and exception/class names).

    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
     d
    -1.63
    ll
    -1.48
    OS
    -1.48
     n
    -1.42
     h
    -1.40
     s
    -1.37
     a
    -1.36
     =
    -1.35
     таким
    -1.33
     p
    -1.31
    POSITIVE LOGITS
     intelligente
    1.41
     velg
    1.34
    
    1.32
    棡
    1.30
     keramik
    1.30
     prachtig
    1.28
     barna
    1.28
     ideen
    1.27
    ⇲
    1.27
    gæ
    1.25
    Activations Density 0.041%

    No Known Activations