© 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. 42794
    Prev
    Next
    INDEX
    Explanations

    Caspar, despair

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

    The neuron is specialized in spotting mentions of “despair” (and its morphological variants) in text.

    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
    ⸫
    -3.45
    嘥
    -3.17
    
    -3.13
     皇族
    -3.11
    賸
    -3.09
    訁
    -3.06
    
    -2.98
    コチラ
    -2.94
    扨
    -2.88
     และ
    -2.86
    POSITIVE LOGITS
    .
    4.06
    {
    3.22
    e
    2.94
    )
    2.88
     During
    2.77
    ;
    2.69
    or
    2.63
     Despite
    2.61
     Although
    2.59
     After
    2.58
    Activations Density 0.001%

    No Known Activations