© 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. 123709
    Prev
    Next
    INDEX
    Explanations

    code, dates, or section titles

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

    type casting or conversion operations in code (particularly the "cast<" syntax in C++).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     misma
    -1.60
     которые
    -1.55
     каждый
    -1.54
    ag
    -1.52
     referenced
    -1.41
    Organisator
    -1.41
    ot
    -1.40
    臯
    -1.40
    随便
    -1.39
    هم
    -1.38
    POSITIVE LOGITS
    for
    1.56
    ﺲ
    1.52
    fficking
    1.52
     downside
    1.47
    essayer
    1.47
    但是在
    1.45
    diyah
    1.43
    薔
    1.41
     светло
    1.41
    тися
    1.41
    Activations Density 0.000%

    No Known Activations