© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13159
    Prev
    Next
    INDEX
    Explanations

    words starting with pre

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

    This neuron detects highly technical, patent-style process descriptions—especially terms around conditioning/orientation steps in manufacturing (e.g. “conditioning,” “brought to orientation temperature,” “molded preforms,” etc.).

    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
    伸び
    -0.87
    chowy
    -0.85
    hidup
    -0.79
     getResource
    -0.79
    mita
    -0.77
     geraten
    -0.76
     pracov
    -0.76
     léč
    -0.75
     modelli
    -0.75
    sisten
    -0.75
    POSITIVE LOGITS
     preparation
    1.73
     preparatory
    1.72
     precondition
    1.56
     prepare
    1.52
     before
    1.51
     prepares
    1.44
     preparations
    1.43
     preparing
    1.42
     prerequisite
    1.41
     prep
    1.38
    Activations Density 0.178%

    No Known Activations