© 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. 61176
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

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

    The neuron fires on formal transitional or discourse‐marker words (e.g. “However,” “Accordingly,” “hereinafter,” etc.) that indicate shifts or references in a technical/legal text.

    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
     AspNetCore
    -1.84
    ↵
    -1.68
    寕
    -1.54
     also
    -1.48
    
    -1.41
    ﹕
    -1.39
     verheiratet
    -1.38
    ?
    -1.36
    .”
    -1.34
     apiKey
    -1.32
    POSITIVE LOGITS
    2
    1.46
    ۹
    1.40
    eight
    1.36
    หรือ
    1.31
    ån
    1.31
     lieu
    1.30
     reducido
    1.28
    媪
    1.27
     上午
    1.27
    除了
    1.24
    Activations Density 0.010%

    No Known Activations