© 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. 22-GEMMASCOPE-RES-131K
    4. 68650
    Prev
    Next
    INDEX
    Explanations

    Bible translations and compilations

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

    The neuron consistently lights up on document metadata—things like section headings, labels, version numbers, and other technical “book‐keeping” terms (e.g. “translation,” “version,” “Font,” “Size,” “Bible,” numeric IDs, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    rightarrow
    -1.37
    ७
    -1.36
    ernalia
    -1.32
    primaryStage
    -1.30
     but
    -1.29
    ]==
    -1.27
     inside
    -1.24
     build
    -1.23
    ९
    -1.23
     and
    -1.23
    POSITIVE LOGITS
     oignon
    1.39
    Distribución
    1.38
     ویتامین
    1.35
     Edizioni
    1.34
     atlet
    1.33
    pherds
    1.30
    chränkungen
    1.27
     hende
    1.27
     roul
    1.27
     favoris
    1.24
    Activations Density 0.020%

    No Known Activations