© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72606
    Prev
    Next
    INDEX
    Explanations

    slowly followed by verbs

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

    The neuron sharply activates on the adverb “slowly.”

    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
    ↵↵
    -2.97
     ‘
    -2.75
     &
    -2.66
    тися
    -2.45
    s
    -2.34
    咙
    -2.33
    挲
    -2.28
     fű
    -2.23
    sistors
    -2.20
     egyéb
    -2.20
    POSITIVE LOGITS
    鹮
    3.23
     放題
    2.80
    the
    2.69
    莚
    2.56
    鲧
    2.56
    ."
    2.56
    鸶
    2.45
     場所
    2.44
    寕
    2.42
     Houſe
    2.39
    Activations Density 0.002%

    No Known Activations