© 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. 10-GEMMASCOPE-RES-131K
    7. 22303
    Prev
    Next
    INDEX
    Explanations

    lamenting and decrying

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

    The neuron activates on verbs expressing complaint or regret—words like “lament,” “decry,” and “deplore.”

    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
     embody
    -2.08
     Whether
    -2.06
     ensures
    -2.06
     forego
    -2.06
     examinar
    -2.05
     assurance
    -2.03
     maintain
    -2.02
     criticize
    -2.00
     invoke
    -1.98
     assist
    -1.95
    POSITIVE LOGITS
    亖
    2.41
    ↵
    2.30
    ſſel
    2.20
    鸱
    2.19
     tinham
    2.09
    .
    2.06
    鸶
    2.05
     começ
    2.03
    selbe
    1.97
    蚡
    1.95
    Activations Density 0.004%

    No Known Activations