© 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. 130983
    Prev
    Next
    INDEX
    Explanations

    Haskell code and related syntax

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

    This neuron fires on Haskell‐specific code tokens—especially LANGUAGE pragmas, the names “Haskell” or “GHC,” and related module/compiler keywords.

    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
     kommunen
    -1.37
     défauts
    -1.32
    剩下
    -1.28
     nying
    -1.28
     มาก
    -1.26
     mêmes
    -1.23
    čiau
    -1.23
    愃
    -1.23
    मिक
    -1.22
    笵
    -1.22
    POSITIVE LOGITS
     najbol
    1.32
    *
    1.26
     žá
    1.20
     zato
    1.20
     on
    1.16
     you
    1.16
    snp
    1.15
    nością
    1.14
     Abends
    1.14
            
    1.13
    Activations Density 0.027%

    No Known Activations