© 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. 91322
    Prev
    Next
    INDEX
    Explanations

    copyright license version license

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

    This neuron responds strongly to the phrase “full of.”

    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
     får
    -0.91
    icom
    -0.82
    жди
    -0.81
     iterations
    -0.81
     ў
    -0.81
    fabrik
    -0.79
    pd
    -0.79
     swojej
    -0.78
     Voss
    -0.77
    ріб
    -0.77
    POSITIVE LOGITS
     viciss
    0.98
     democra
    0.94
     நட
    0.91
     vigorous
    0.91
     ordinary
    0.88
     procra
    0.86
     rigorous
    0.86
     steady
    0.86
     violences
    0.85
     exquisite
    0.84
    Activations Density 0.002%

    No Known Activations