© 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. 101812
    Prev
    Next
    INDEX
    Explanations

    package management and build tools

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

    technical software and system configuration terms, particularly related to Linux/Unix tools and programming environments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of specific software or protocol names (i.e. technology acronyms and package names).

    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
    其他的
    -1.45
    resultat
    -1.42
    。】
    -1.39
    interna
    -1.32
     предоставля
    -1.31
    Etape
    -1.30
    asst
    -1.30
    〼
    -1.30
    Eerste
    -1.29
    Reached
    -1.28
    POSITIVE LOGITS
     you
    1.71
     himself
    1.31
    
    1.25
    umpulkan
    1.21
    
    1.20
     २०
    1.16
    ~
    1.15
    </h3>
    1.14
     kupić
    1.13
    yled
    1.12
    Activations Density 0.155%

    No Known Activations