© 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. 11595
    Prev
    Next
    INDEX
    Explanations

    start of section or content

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

    The neuron fires on occurrences of the “=>” symbol (the fat-arrow or conditional/operator shorthand) in code.

    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
    Controllo
    -1.46
    二日
    -1.34
    했습니다
    -1.32
     médicas
    -1.31
    ၜ
    -1.30
    Вариант
    -1.28
    ěř
    -1.27
    Nieuw
    -1.23
    未完
    -1.23
    蜂蜜
    -1.23
    POSITIVE LOGITS
    埽
    1.45
    <<<<
    1.44
     réduire
    1.43
    
    1.43
    早已
    1.42
     COURSE
    1.41
    俛
    1.38
     prévenir
    1.37
    莫名
    1.36
    (
    1.36
    Activations Density 0.004%

    No Known Activations