© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107162
    Prev
    Next
    INDEX
    Explanations

    marine creatures and ponds

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

    terms related to marine or aquatic environments, including aquariums, sea creatures, and ocean-related terminology.

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

    The neuron fires on mentions of marine‐related venues or attractions (e.g. aquarium, oceanographic institute, shark‐cage diving).

    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
     utafitiHapana
    -0.77
     trái
    -0.75
    蟬
    -0.73
    鹿
    -0.73
     contentious
    -0.73
     deer
    -0.73
     yo
    -0.72
     级
    -0.72
    クル
    -0.71
     Vog
    -0.71
    POSITIVE LOGITS
     tanks
    1.23
     tank
    1.10
     aquarium
    1.06
     husbandry
    1.05
     exhibit
    1.01
     Aquarium
    0.99
    tank
    0.97
    Tank
    0.96
     Ripley
    0.95
     exhibits
    0.95
    Activations Density 0.008%

    No Known Activations