© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85606
    Prev
    Next
    INDEX
    Explanations

    introducing a supposition

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

    The neuron detects hedging or subjective opinion phrases (e.g. “I suppose,” “it’s subjective to a degree”).

    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
    ”，
    -1.78
     is
    -1.77
    ”（
    -1.69
    )-
    -1.63
     okt
    -1.56
     быстро
    -1.52
     سیستم
    -1.52
    ﹕
    -1.51
     celui
    -1.49
    ”、“
    -1.47
    POSITIVE LOGITS
     nhưng
    1.93
    讥
    1.93
    ,“
    1.83
     αλλά
    1.77
     einzigartigen
    1.76
     einzigartige
    1.73
     zusätzlichen
    1.70
     jenen
    1.69
     leichten
    1.68
     gewünschten
    1.66
    Activations Density 0.021%

    No Known Activations