© 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. 23962
    Prev
    Next
    INDEX
    Explanations

    temporal kinetics

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

    The neuron fires strongly on punctuation sequences that open or delimit markup blocks—especially the “{\” token in RTF and similar brace‐plus‐symbol patterns (e.g. “]{” in LaTeX).

    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
    朝の
    -1.51
     zaidi
    -1.51
     Gln
    -1.50
    TemporalType
    -1.49
     フリース
    -1.48
    🪕
    -1.48
    接下来的
    -1.46
    搁
    -1.46
    ことはありません
    -1.46
    されない
    -1.45
    POSITIVE LOGITS
     Which
    1.98
     According
    1.89
    (
    1.84
     Notably
    1.83
    <b>
    1.75
     Although
    1.73
     Of
    1.73
     While
    1.69
     Ideally
    1.67
     “…
    1.67
    Activations Density 0.006%

    No Known Activations