© 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. 104375
    Prev
    Next
    INDEX
    Explanations

    le following text

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

    The neuron is a detector for the two‐letter sequence “le” wherever it occurs.

    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
    //
    -2.72
    s
    -2.44
    e
    -2.27
     как
    -2.25
     других
    -2.16
    le
    -2.09
    または
    -2.05
    i
    -2.00
     of
    -1.95
    ру
    -1.93
    POSITIVE LOGITS
    
    2.58
    呶
    2.42
    泚
    2.28
    詎
    2.23
     producenta
    2.19
    ⬯
    2.14
    
    2.03
     Meningkatkan
    2.02
    了出去
    2.00
    敉
    2.00
    Activations Density 0.003%

    No Known Activations