© 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. 34-GEMMASCOPE-RES-131K
    7. 81525
    Prev
    Next
    INDEX
    Explanations

    regrets and negative judgments

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

    The neuron responds to words expressing personal negative sentiments (e.g. regret, fear, annoyance).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     different
    -1.09
    🗹
    -1.01
     also
    -0.99
     restoration
    -0.98
     perguntou
    -0.95
     fulfillment
    -0.94
     encontrar
    -0.94
     reorganization
    -0.93
     successful
    -0.91
     conquering
    -0.91
    POSITIVE LOGITS
     letting
    1.68
     sending
    1.63
     entrust
    1.45
     allowing
    1.44
     asking
    1.38
     wanting
    1.28
     placing
    1.27
     putting
    1.25
     leaving
    1.25
    将
    1.24
    Activations Density 0.081%

    No Known Activations