© 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. 9822
    Prev
    Next
    INDEX
    Explanations

    clarifying phrases

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

    This neuron detects hedging or clarifying discourse markers like “to be sure,” “to be clear,” 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_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
     to
    -1.69
    业主
    -1.66
    と言えば
    -1.57
    のお知らせ
    -1.55
    %;
    -1.54
    甞
    -1.52
    {
    -1.52
    ceptable
    -1.48
    心に
    -1.47
    我又
    -1.47
    POSITIVE LOGITS
     of
    1.95
    0
    1.92
    4
    1.80
     also
    1.59
     But
    1.56
    骤
    1.52
    ↑↑↑</
    1.51
    6
    1.51
     This
    1.45
     únicamente
    1.45
    Activations Density 0.005%

    No Known Activations