© 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. 33678
    Prev
    Next
    INDEX
    Explanations

    Mount or Garden locations

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

    This neuron fires on the opening words of individual biblical verses or sections, i.e. the very first few tokens at the start of each verse.

    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
    abolic
    -0.81
    楽しみです
    -0.74
     нужен
    -0.74
    خدا
    -0.74
    simu
    -0.74
    鐲
    -0.73
    絆
    -0.73
    後的
    -0.72
    挑选
    -0.71
    ownerId
    -0.71
    POSITIVE LOGITS
     Mount
    1.08
     Garden
    0.90
    Mount
    0.89
     MPEG
    0.79
    mount
    0.78
    graphers
    0.76
    Garden
    0.76
    adil
    0.75
     mount
    0.73
     mounts
    0.73
    Activations Density 0.015%

    No Known Activations