© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20642
    Prev
    Next
    INDEX
    Explanations

    `td::` and `.?` sequences

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

    The neuron responds to runs of non‐standard symbols and stray punctuation (i.e. odd characters/artifacts from formatting) rather than ordinary words.

    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
     superbly
    -1.88
     enhances
    -1.88
     reinforces
    -1.83
    地说
    -1.74
     reduces
    -1.70
    _
    -1.68
     HUGE
    -1.67
     bolster
    -1.65
     nahezu
    -1.64
     Often
    -1.62
    POSITIVE LOGITS
    ANAS
    1.67
    !!!!!!!
    1.61
     '
    1.54
    蚡
    1.52
     ,'
    1.50
    carnated
    1.48
     haar
    1.48
    の中の
    1.46
     !!!!
    1.45
     très
    1.44
    Activations Density 0.008%

    No Known Activations