© 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. 22-GEMMASCOPE-RES-131K
    7. 12876
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

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

    The neuron reliably lights up on code identifiers—variable and parameter names—rather than on ordinary English words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     délais
    -1.44
     cinquième
    -1.41
    makes
    -1.37
     Dinas
    -1.36
     coûts
    -1.36
     hadden
    -1.35
    hre
    -1.35
    actéristi
    -1.34
     éché
    -1.33
    hio
    -1.32
    POSITIVE LOGITS
     almost
    1.65
     every
    1.62
     now
    1.60
     really
    1.54
     probably
    1.52
     actually
    1.51
     one
    1.50
     very
    1.48
     this
    1.43
     which
    1.43
    Activations Density 0.003%

    No Known Activations