© 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. 45263
    Prev
    Next
    INDEX
    Explanations

    uncertain outcomes

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

    The neuron flags uses of the word “uncertain,” marking expressions of uncertainty or indeterminacy.

    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
    そも
    -2.64
    tedì
    -2.63
    két
    -2.42
     increíbles
    -2.41
    исленность
    -2.39
     vécu
    -2.28
    菹
    -2.28
     Añade
    -2.27
     conséquent
    -2.25
    ☆☆☆☆
    -2.25
    POSITIVE LOGITS
    an
    3.09
    ная
    2.53
     него
    2.50
    0
    2.45
    {
    2.22
     (“
    2.13
    .
    2.11
     –
    2.09
     was
    2.03
    m
    2.00
    Activations Density 0.002%

    No Known Activations