© 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. 34-GEMMASCOPE-RES-131K
    4. 50082
    Prev
    Next
    INDEX
    Explanations

    death, separation, and darkness

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

    The neuron is strongly activated by common little “glue” words—prepositions, conjunctions, and articles (e.g. in, of, and, the, from, off).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    していきます
    -0.85
     না
    -0.84
    Xuất
    -0.82
    uiente
    -0.82
    🌔
    -0.81
    vantaged
    -0.79
    潤
    -0.79
    櫛
    -0.75
    ragalactic
    -0.75
     convulsions
    -0.75
    POSITIVE LOGITS
     darkness
    1.27
     wszel
    1.16
    一切
    1.06
     segala
    1.02
     everything
    1.00
    voer
    0.99
     any
    0.97
     anything
    0.96
     death
    0.96
     Redacción
    0.95
    Activations Density 0.019%

    No Known Activations