© 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. 22-GEMMASCOPE-RES-131K
    4. 71457
    Prev
    Next
    INDEX
    Explanations

    nouns and their descriptions

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

    specific components or elements within formal documents like forms, articles, websites, or systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric tokens and measurements (integers or decimals).

    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
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.85
     wszystkie
    -0.85
     muualla
    -0.84
    neapolis
    -0.84
     schwach
    -0.83
    妝
    -0.82
    iança
    -0.81
    tev
    -0.80
    λων
    -0.79
     herab
    -0.78
    POSITIVE LOGITS
    而言
    1.18
     only
    0.95
     kuv
    0.92
    ší
    0.89
     可愛い
    0.87
     katun
    0.87
    来说
    0.85
     basically
    0.84
     dingin
    0.84
    Когда
    0.84
    Activations Density 0.115%

    No Known Activations