© 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. 10-GEMMASCOPE-RES-131K
    7. 42701
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in ly or after conjunctions/punctuation

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

    The neuron is firing on numeric tokens (digits, percentages, decimal numbers, numeric measurements).

    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
    鼇
    -1.68
    ？！”
    -1.66
     fű
    -1.60
    此外
    -1.58
    퐹
    -1.57
    יתוף
    -1.53
    ߀
    -1.53
     suffrage
    -1.52
    豸
    -1.50
     mencegah
    -1.48
    POSITIVE LOGITS
    )
    2.28
    c
    2.19
    f
    2.11
    $
    2.09
    ]
    2.06
    ly
    2.03
    si
    1.98
    *
    1.95
    |
    1.92
     $
    1.91
    Activations Density 0.077%

    No Known Activations