© 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. 42688
    Prev
    Next
    INDEX
    Explanations

    preparation contexts

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

    This neuron detects the “Prep” heading (as in “Prep Time” or “Prep for …”) in recipe-style instruction sections.

    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
    }
    -2.94
    焄
    -2.58
     Their
    -2.50
    豨
    -2.36
    ⟝
    -2.31
    蒟
    -2.31
     erwähnten
    -2.23
    辚
    -2.19
    咈
    -2.17
    鮰
    -2.17
    POSITIVE LOGITS
    佧
    2.48
     ultimi
    2.23
     Татьяна
    2.22
     elegance
    2.19
     importer
    2.17
     ounce
    2.13
    同时
    2.11
     essere
    2.09
     effray
    2.08
     inconvénients
    2.08
    Activations Density 0.003%

    No Known Activations