© 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. 84627
    Prev
    Next
    INDEX
    Explanations

    class, typeof, return

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

    The neuron fires on programming tokens that refer to types or type‐reflection operations (e.g. Class, Type, typeof, forName, ParameterizedType).

    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
    ivant
    -0.83
    baut
    -0.80
    newBuilder
    -0.79
    korn
    -0.79
    gnato
    -0.77
    album
    -0.77
     albums
    -0.77
    tiger
    -0.76
     ::
    -0.75
     Medien
    -0.75
    POSITIVE LOGITS
     "".
    0.92
    לחה
    0.89
     beque
    0.84
     کردم
    0.81
     précédentes
    0.79
     Stopped
    0.77
    çok
    0.76
    ImgUrl
    0.76
    員工
    0.75
     Altura
    0.75
    Activations Density 0.008%

    No Known Activations