© 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. 3686
    Prev
    Next
    INDEX
    Explanations

    version control systems

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

    The neuron detects mentions of version‐control systems and related terms (e.g. VCS, Git, CVS, Subversion, source/revision control).

    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
     esquecer
    -1.35
    immagine
    -1.33
     conhecer
    -1.30
     uiteindelijk
    -1.29
     faltan
    -1.28
    した後
    -1.28
     compartilhar
    -1.24
     frucht
    -1.22
     wich
    -1.20
     băr
    -1.20
    POSITIVE LOGITS
    ing
    1.93
    ОВА
    1.45
     tega
    1.44
    ￦
    1.30
    ActionMode
    1.28
    te
    1.28
    欒
    1.28
    *///
    1.27
    "))
    1.27
     июня
    1.26
    Activations Density 0.158%

    No Known Activations