© 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. 116703
    Prev
    Next
    INDEX
    Explanations

    mountain and mountain-like names

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

    This neuron detects substrings that mean “mountain” (e.g. “berg,” “mountain,” “yama,” “shan,” etc.) in various names.

    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
    imming
    -0.94
     angus
    -0.88
     armada
    -0.81
    かた
    -0.80
    httpd
    -0.79
     Debe
    -0.79
    "__
    -0.79
     archer
    -0.79
     Algae
    -0.77
     KNIGHT
    -0.77
    POSITIVE LOGITS
     mountain
    1.23
     mountains
    1.08
     Mountain
    1.02
    side
    1.02
    ⛰
    1.01
    top
    0.98
     range
    0.97
    🏔
    0.93
    ous
    0.92
     Gebir
    0.88
    Activations Density 0.006%

    No Known Activations