© 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. 130878
    Prev
    Next
    INDEX
    Explanations

    disappointing outcomes

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

    The neuron fires on the “disappoint-” root (e.g. “disappointed,” “disappointing”), i.e. expressions of disappointment.

    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
     установка
    -2.17
     This
    -2.08
     Когда
    -2.06
    嵛
    -2.05
     selben
    -2.00
     It
    -1.94
    ៚
    -1.92
     esteemed
    -1.88
    D
    -1.87
    必然
    -1.86
    POSITIVE LOGITS
    {
    2.81
    _
    2.39
    [
    1.98
    сії
    1.90
    fication
    1.88
    觊
    1.88
    ’
    1.77
     lele
    1.75
    mentazione
    1.73
    りました
    1.73
    Activations Density 0.009%

    No Known Activations