© 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. 111266
    Prev
    Next
    INDEX
    Explanations

    $Date and $Revision markers

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

    metadata headers in source code files, particularly file and version information in comment blocks.

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

    The neuron is detecting version‐control metadata markers (e.g. “$Date:$”, “$Revision:$”, colon‐delimited version fields) in file header comments.

    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
     industrias
    -1.37
     burbujas
    -1.31
     trzech
    -1.30
     къде
    -1.30
     wysokości
    -1.25
    ↵↵
    -1.24
     sabias
    -1.22
     humedad
    -1.21
     calientes
    -1.21
     “
    -1.20
    POSITIVE LOGITS
    Regardless
    1.63
    Although
    1.55
     to
    1.51
     surabaya
    1.45
    Размеры
    1.40
     kekasih
    1.38
    Often
    1.36
    Whether
    1.34
     Meksi
    1.34
     Although
    1.34
    Activations Density 0.280%

    No Known Activations