© 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. 110731
    Prev
    Next
    INDEX
    Explanations

    I'm not sure

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

    The neuron detects hedging or uncertainty expressions, most strongly “not sure” (and variants like “not sure if/how/that…”).

    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
    -2.02
    ]
    -1.91
    ～～～～
    -1.90
     notwendig
    -1.88
     結果
    -1.83
    Those
    -1.77
     вернулся
    -1.77
     فهي
    -1.77
     communs
    -1.75
     temporaire
    -1.72
    POSITIVE LOGITS
     about
    1.88
    t
    1.86
     apprehension
    1.85
    ՚
    1.76
     whether
    1.71
    »,
    1.70
    違って
    1.67
    Y
    1.66
    U
    1.64
     começaram
    1.63
    Activations Density 0.012%

    No Known Activations