© 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. 23955
    Prev
    Next
    INDEX
    Explanations

    law, license, Metal Blade

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

    The neuron is keyed to structural and markup delimiters—things like “Q:”, “#”, “<?php”, colons, and other section-heading or code-delimiter 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
    ⽽
    -1.87
     powerfully
    -1.78
     disregarding
    -1.77
     captivated
    -1.71
     defying
    -1.69
     needlessly
    -1.69
     ignited
    -1.67
     comprehensively
    -1.63
     orchestrated
    -1.62
     uncovering
    -1.62
    POSITIVE LOGITS
     and
    1.88
     &
    1.37
    ׇ
    1.30
     this
    1.30
     to
    1.24
     --
    1.15
     ''
    1.15
    libatkan
    1.11
    ِّ
    1.09
     have
    1.06
    Activations Density 34.047%

    No Known Activations