© 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. 31116
    Prev
    Next
    INDEX
    Explanations

    typename Tag, typename Tag2

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

    The neuron strongly activates on programming‐language declaration keywords (e.g. typename, let, var, const) across different code snippets.

    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
     siihen
    -1.11
    ņem
    -1.02
     gratuites
    -0.94
     genuine
    -0.94
     disponibilités
    -0.93
    ColumnHeaders
    -0.93
    の人生
    -0.90
     arvio
    -0.90
    拢
    -0.89
    ﺇ
    -0.89
    POSITIVE LOGITS
    ншот
    0.99
     determinants
    0.98
    捗
    0.91
    ूरत
    0.90
    衣裙
    0.90
     ornate
    0.89
     worin
    0.87
     коне
    0.86
     oignon
    0.85
     следующие
    0.84
    Activations Density 0.002%

    No Known Activations