© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79513
    Prev
    Next
    INDEX
    Explanations

    Australian nature and wildlife

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

    words and phrases related to natural environments, particularly forests, trees, and outdoor landscapes.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    The neuron is a high‐activation detector for content nouns—especially place names and geographic or physical feature terms.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     tillage
    -0.88
     alfalfa
    -0.87
     sherds
    -0.78
    Sam
    -0.76
     Brant
    -0.76
    Sage
    -0.75
     Saviour
    -0.73
    সূত্র
    -0.72
     Sam
    -0.71
    support
    -0.71
    POSITIVE LOGITS
    Emu
    1.33
     Eucalyptus
    1.33
    Eucalyptus
    1.33
     eucalyptus
    1.27
     euc
    1.22
     kangaroo
    1.18
     emu
    1.13
     koala
    1.06
     poss
    1.05
     rainforest
    1.03
    Activations Density 0.057%

    No Known Activations