© 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. 34-GEMMASCOPE-RES-131K
    7. 53925
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

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

    The neuron is picking out single‐quote characters (the apostrophe tokens used to delimit string literals).

    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
    ffles
    -0.80
     mémor
    -0.79
    /*
    -0.79
    ⅛
    -0.78
    Ene
    -0.78
    ANIEL
    -0.77
    levy
    -0.76
     Kategorie
    -0.76
    šas
    -0.75
     Ababa
    -0.74
    POSITIVE LOGITS
    class
    0.91
     class
    0.90
     method
    0.79
    🌫
    0.78
     presentato
    0.78
    DialogInterface
    0.75
    🌪
    0.75
     parfait
    0.73
     Priorities
    0.73
     observ
    0.73
    Activations Density 0.012%

    No Known Activations