© 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. 10-GEMMASCOPE-RES-131K
    4. 12236
    Prev
    Next
    INDEX
    Explanations

    research studies comparing outcomes

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

    This neuron detects the key connective words and gerunds that structure formal titles or headings (e.g. “of,” “for,” “comparing,” “specializing”) in technical or product descriptions.

    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
     своих
    -1.53
     estação
    -1.48
    }}
    
    -1.47
    "/",
    -1.45
    pří
    -1.41
    可愛い
    -1.41
    かわいい
    -1.41
    卺
    -1.41
     trilha
    -1.39
    geschwindigkeit
    -1.38
    POSITIVE LOGITS
     for
    1.51
     in
    1.36
    了一些
    1.32
     داشتند
    1.29
     Maybe
    1.28
     Mannes
    1.24
     or
    1.23
     not
    1.23
     Makes
    1.23
     getChild
    1.23
    Activations Density 0.360%

    No Known Activations