© 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. 86703
    Prev
    Next
    INDEX
    Explanations

    natural followed by noun

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

    The neuron specifically fires on the word “natural” (in any context or casing).

    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
    ৢ
    -2.28
    赑
    -2.14
     :).
    -2.03
    ⎚
    -2.00
    ]$
    -1.94
    玙
    -1.93
     caveats
    -1.91
    馓
    -1.91
    OUTUBE
    -1.87
     Japón
    -1.81
    POSITIVE LOGITS
    呖
    2.16
     glaubte
    2.02
    natural
    1.97
     certainly
    1.96
    Having
    1.94
     naturais
    1.90
    Perhaps
    1.87
    However
    1.87
    “
    1.85
     natürliche
    1.84
    Activations Density 0.036%

    No Known Activations