© 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. 34-GEMMASCOPE-RES-131K
    7. 75510
    Prev
    Next
    INDEX
    Explanations

    easier, simpler, faster

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

    The neuron fires on common discourse‐marker adverbs and hedges—especially “just” (and similar softening words like “probably,” “easier,” “it’s,” 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_34/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
    所说
    -0.94
     comentários
    -0.90
     basan
    -0.90
     signifie
    -0.88
    ţele
    -0.87
    immel
    -0.85
     normalement
    -0.82
    毫不
    -0.82
     bahkan
    -0.81
    日から
    -0.81
    POSITIVE LOGITS
     easier
    5.09
     simpler
    3.61
     easiest
    3.59
    easier
    3.41
     Easier
    3.31
     проще
    3.27
     safer
    3.22
    Easier
    3.20
     faster
    2.98
     quicker
    2.95
    Activations Density 0.068%

    No Known Activations