© 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. 10-GEMMASCOPE-RES-131K
    7. 69353
    Prev
    Next
    INDEX
    Explanations

    seeking various things

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

    The neuron activates specifically on the word “seeking” (in any form or casing).

    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
    j
    -2.70
     énergie
    -2.42
    ﹆
    -2.36
     aspire
    -2.31
    いの
    -2.23
    z
    -2.17
    蚱
    -2.17
     такую
    -2.13
    价格
    -2.11
     проектов
    -2.06
    POSITIVE LOGITS
    趼
    2.86
    阄
    2.48
    
    2.39
    趵
    2.33
    蠊
    2.22
    颺
    2.20
     gustaMe
    2.20
    ญี่ป
    2.19
    淠
    2.19
    ierung
    2.17
    Activations Density 0.005%

    No Known Activations