© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47542
    Prev
    Next
    INDEX
    Explanations

    urgency

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

    This neuron strongly activates on words expressing urgency or a pressing need (e.g., “urgent,” “urgency,” “pressing”).

    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
     preciosas
    -2.14
     puntas
    -2.14
     ร์
    -2.14
    雱
    -2.13
    噥
    -2.09
    訁
    -2.09
    鹋
    -2.08
    댔
    -2.03
     doloroso
    -2.02
    ༛
    -1.99
    POSITIVE LOGITS
     urgency
    2.48
     in
    2.11
     and
    2.09
    ↵
    1.89
     of
    1.85
    .
    1.82
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.79
    馄
    1.73
     ditangkap
    1.69
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.67
    Activations Density 0.004%

    No Known Activations