© 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. 47793
    Prev
    Next
    INDEX
    Explanations

    expressing uncertainty or doubt

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

    The neuron flags occurrences of the word “unsure,” i.e. expressions of uncertainty.

    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
    </b>
    -3.22
     In
    -2.47
     ”
    -2.42
     The
    -2.42
    a
    -2.30
    -
    -2.30
    an
    -2.25
    i
    -2.22
     [
    -2.09
     concernés
    -2.08
    POSITIVE LOGITS
    鶿
    2.56
    шают
    2.47
    </h3>
    2.47
    ₶
    2.36
    𐐀
    2.33
    ⸂
    2.31
    厹
    2.30
    itarias
    2.30
     ابتد
    2.28
     ส์
    2.27
    Activations Density 0.001%

    No Known Activations