© 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. 71276
    Prev
    Next
    INDEX
    Explanations

    babel transpilation

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

    This neuron detects occurrences of “babel” (and related substrings) in code or configuration.

    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
     ‘
    -2.80
    '
    -2.55
    ?’
    -2.45
     esmal
    -2.36
    愎
    -2.25
     acrí
    -2.25
     maquilla
    -2.23
     cerámica
    -2.23
    ⧠
    -2.19
     (‘
    -2.17
    POSITIVE LOGITS
    ].
    2.42
    {
    2.39
    e
    2.28
     selepas
    2.19
    </b>
    2.11
    where
    2.09
     awakeFromNib
    2.06
    ců
    2.03
    iſter
    2.03
    糬
    1.91
    Activations Density 0.002%

    No Known Activations