© 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. 12026
    Prev
    Next
    INDEX
    Explanations

    programming terms

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

    tokens related to .NET/C# code, particularly class names, namespaces, and API references in technical documentation or programming contexts.

    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
    其他
    -1.25
     هناك
    -1.16
     is
    -1.16
    ється
    -1.15
     pamoja
    -1.13
    ные
    -1.12
     інші
    -1.10
     سایر
    -1.09
    ють
    -1.08
     была
    -1.08
    POSITIVE LOGITS
    шкой
    1.26
     internation
    1.13
    ėje
    1.09
    เหรียญ
    1.07
     juillet
    1.06
    сети
    1.05
     childcare
    1.05
     visar
    1.05
    zünd
    1.04
    кистан
    1.04
    Activations Density 0.144%

    No Known Activations