© 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. 75143
    Prev
    Next
    INDEX
    Explanations

    awaiting events or action

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

    This neuron detects occurrences of “await” (e.g. “awaiting,” “awaits”)—verbs expressing waiting or anticipation.

    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
     \
    -2.56
    },
    -2.50
    rítica
    -2.22
     is
    -2.11
    ᯾
    -2.03
    }{
    -2.00
    凿
    -2.00
    食い
    -1.99
    铤
    -1.98
    欒
    -1.97
    POSITIVE LOGITS
    谖
    2.53
    の種類
    2.31
    是
    2.27
     Something
    2.22
    不是
    2.14
    ᨈ
    2.13
    ﮯ
    2.11
    퐹
    2.11
    
    2.11
     This
    2.08
    Activations Density 0.004%

    No Known Activations