© 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. 10276
    Prev
    Next
    INDEX
    Explanations

    file descriptors and code

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

    the token "@file" in source code file headers and documentation comments.

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

    The neuron is triggered by non‐word tokens that serve as document markers—specifically ellipses (“…”) and file‐tag tokens (like “file” in code comment headers).

    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
     out
    -2.00
     to
    -1.98
     dazzling
    -1.70
     helped
    -1.67
     through
    -1.64
     intensely
    -1.63
     veces
    -1.57
     for
    -1.54
     had
    -1.53
     sehr
    -1.53
    POSITIVE LOGITS
     flink
    1.66
     deler
    1.56
     uan
    1.52
     spits
    1.51
     MAJOR
    1.49
     vold
    1.49
     simpel
    1.48
    䐀
    1.47
    locene
    1.47
     levering
    1.46
    Activations Density 0.000%

    No Known Activations