© 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. 69429
    Prev
    Next
    INDEX
    Explanations

    in this way, in this manner

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

    The neuron fires on discourse-linking expressions of manner—specifically on the word “way” (and its variants) in phrases like “in this way,” “in the same way,” or “in this manner.”

    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
    恳
    -2.03
    ?
    -2.03
    ":
    -1.92
    歿
    -1.90
    あります
    -1.90
    してます
    -1.88
    Suka
    -1.84
    ?’
    -1.84
     nahezu
    -1.81
    PAIGN
    -1.80
    POSITIVE LOGITS
    “
    3.13
    1
    2.31
    ]
    2.30
    。
    2.23
    3
    2.16
    「
    2.03
    ``
    2.00
     \"
    2.00
    the
    1.96
    ”
    1.95
    Activations Density 0.010%

    No Known Activations