© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60239
    Prev
    Next
    INDEX
    Explanations

    code/markup elements and foreign languages

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

    The neuron never fires on any of these passages—it appears to be inactive (a “dead” neuron).

    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
     especially
    -0.93
     know
    -0.84
     specifically
    -0.82
    ólogos
    -0.81
    ！”
    -0.81
     other
    -0.80
     highlighting
    -0.80
    praš
    -0.79
     highlighted
    -0.79
    зации
    -0.79
    POSITIVE LOGITS
    <table>
    1.05
     nossa
    0.93
    Wikimedia
    0.92
     meilleures
    0.90
    ботинки
    0.86
    Viki
    0.85
    пом
    0.84
     nier
    0.81
    洒落
    0.80
    ⁷
    0.80
    Activations Density 0.002%

    No Known Activations