© 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. 60596
    Prev
    Next
    INDEX
    Explanations

    t

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

    The neuron flags tokens in first-person “I” statements expressing uncertainty or inability (e.g. “I don’t,” “my understanding,” “can’t for the life of me,” “doesn’t seem”).

    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
    那你
    -1.12
    ']]
    -0.98
    本当は
    -0.98
    我也是
    -0.97
    āci
    -0.96
    arz
    -0.95
    legte
    -0.94
    鹛
    -0.94
    omości
    -0.93
    匿名使用者
    -0.90
    POSITIVE LOGITS
     seems
    7.88
     seem
    7.81
     Seems
    6.38
    Seems
    6.38
     seemed
    6.34
    seems
    6.09
     parece
    5.56
    seem
    5.41
    似乎
    5.38
     scheint
    5.16
    Activations Density 0.492%

    No Known Activations