© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112330
    Prev
    Next
    INDEX
    Explanations

    uncertainty, assessment, or determination

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

    The neuron responds to words that express uncertainty, doubt, difficulty, or limitation.

    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
     are
    -1.30
    eski
    -1.20
    цей
    -1.20
     how
    -1.17
    误
    -1.16
     leopardo
    -1.14
    otriva
    -1.12
    ÁL
    -1.12
    deri
    -1.11
    maras
    -1.09
    POSITIVE LOGITS
     of
    1.50
    ʅ
    1.22
    Antal
    1.20
     until
    1.18
     without
    1.14
    Lietu
    1.10
    -
    1.09
    Pä
    1.08
     dette
    1.06
     هناك
    1.06
    Activations Density 0.193%

    No Known Activations