© 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. 90372
    Prev
    Next
    INDEX
    Explanations

    entering, importing, installing

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

    The neuron is triggered by tokens meaning “enter” (e.g. the Chinese character 入 or related words like 登录/登入 or Indonesian “masuk”).

    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
    E
    -5.16
    S
    -4.28
    J
    -4.22
    C
    -4.16
    O
    -4.09
    M
    -4.03
    F
    -3.86
    R
    -3.84
    A
    -3.80
    K
    -3.80
    POSITIVE LOGITS
    
    3.13
    趼
    2.88
    cích
    2.64
    .''
    2.61
    踅
    2.56
    璈
    2.52
    
    2.48
    衪
    2.45
    潆
    2.44
    Donativos
    2.41
    Activations Density 0.002%

    No Known Activations