© 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. 22-GEMMASCOPE-RES-131K
    7. 65218
    Prev
    Next
    INDEX
    Explanations

    various languages and abstract concepts

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

    The neuron is specialized in spotting numeric tokens and measurements (numbers, decimals, and associated units).

    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
     citazioni
    -0.94
    coroutines
    -0.91
    addMouseListener
    -0.89
    тров
    -0.89
    ępo
    -0.88
    ocument
    -0.87
     république
    -0.86
     sguardo
    -0.86
    Zitat
    -0.86
     boxers
    -0.85
    POSITIVE LOGITS
    这样的
    0.96
     yaklaşık
    0.93
    standigheden
    0.92
    這樣的
    0.86
     miljö
    0.85
     примерно
    0.83
     scenario
    0.82
     yatak
    0.80
     goû
    0.79
     semmi
    0.79
    Activations Density 0.114%

    No Known Activations