© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42517
    Prev
    Next
    INDEX
    Explanations

    public followed by code declarations

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

    The neuron activates primarily on the “public” keyword in code, marking access‐modifier declarations.

    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
    かなり
    -1.81
     stalwart
    -1.55
     kaksi
    -1.52
    labilir
    -1.51
    lossing
    -1.46
     dwóch
    -1.46
    Funciones
    -1.43
    -
    -1.42
    を選び
    -1.41
     sabias
    -1.41
    POSITIVE LOGITS
     animé
    1.65
     romper
    1.64
    餮
    1.56
     {}));
    1.52
     time
    1.50
     enceinte
    1.49
     utama
    1.46
     viera
    1.45
     this
    1.45
     plancha
    1.45
    Activations Density 0.011%

    No Known Activations