© 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. 104042
    Prev
    Next
    INDEX
    Explanations

    documentation markup

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

    documentation and code files, particularly reStructuredText markup, Python docstrings, and technical documentation formatting elements.

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

    The neuron activates on reStructuredText formatting syntax—directives (“..”), inline code/backticks, section underlines (“===”), and related markup tokens.

    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
    ("
    -1.72
     Those
    -1.66
    —
    -1.58
     for
    -1.55
    Their
    -1.52
     masih
    -1.48
    ——
    -1.48
    —"
    -1.44
    してしまった
    -1.42
     STILL
    -1.41
    POSITIVE LOGITS
     densidad
    1.38
     inny
    1.36
    ]').
    1.24
     bemerk
    1.23
     kawa
    1.23
    がこの
    1.22
     douze
    1.20
     trebui
    1.17
     INCRE
    1.16
     elevación
    1.15
    Activations Density 0.130%

    No Known Activations