© 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. 34-GEMMASCOPE-RES-131K
    7. 30857
    Prev
    Next
    INDEX
    Explanations

    strong negative emotions

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

    The neuron fires on words that express strong emotional impacts—especially grief, loss, shock, and related sentiments.

    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
     frustrating
    -1.25
     dissatisfaction
    -1.13
     disappointing
    -1.11
     frustration
    -1.09
     frustrations
    -1.06
     exciting
    -1.02
     irritated
    -1.02
     frustrated
    -1.00
     irritation
    -0.99
    exc
    -0.97
    POSITIVE LOGITS
     devastated
    1.63
     shattered
    1.53
     incons
    1.50
     shaken
    1.44
     shock
    1.38
     devastation
    1.34
    deva
    1.32
     understandably
    1.27
     deva
    1.27
     crushed
    1.21
    Activations Density 0.034%

    No Known Activations