© 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. 65467
    Prev
    Next
    INDEX
    Explanations

    cereals, fish, cryptocurrencies

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

    The neuron is tuned to spot numeric or quantitative tokens—e.g. numbers, counts, measurements, and related data.

    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
    主な
    -0.81
    ционного
    -0.80
    部分は
    -0.80
     oczywiście
    -0.79
    沢山
    -0.79
     aleación
    -0.79
     früheren
    -0.78
    的時候
    -0.78
     religiosos
    -0.78
    masına
    -0.77
    POSITIVE LOGITS
     Ethereum
    0.94
     JPEG
    0.90
     mitral
    0.86
     blackjack
    0.85
     Medicaid
    0.85
     IgG
    0.83
     mixtures
    0.82
     melanoma
    0.81
     cocaine
    0.79
    牛肉
    0.79
    Activations Density 0.415%

    No Known Activations