© 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. 22-GEMMASCOPE-RES-131K
    7. 28131
    Prev
    Next
    INDEX
    Explanations

    intentionally or deliberately

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

    The main thing this neuron does is detect adverbs expressing intentional or deliberate action (e.g., deliberately, intentionally, purposefully).

    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
    跻
    -1.21
    不错的
    -1.21
    Filming
    -1.16
    ﺷ
    -1.13
    orestation
    -1.10
    侄
    -1.08
     salud
    -1.08
    Tambah
    -1.06
    logLevel
    -1.06
    伟大
    -1.05
    POSITIVE LOGITS
    わけではない
    1.14
     berada
    1.14
    故意
    1.13
     soltanto
    1.12
    生
    1.11
     deshalb
    1.09
     bewusst
    1.09
     kept
    1.06
     not
    1.02
     never
    1.01
    Activations Density 0.032%

    No Known Activations