© 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. 98466
    Prev
    Next
    INDEX
    Explanations

    marine animals and seafood

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

    descriptions of marine life and aquatic ecosystems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     apic
    -0.89
    Animal
    -0.87
    lake
    -0.83
    }}+\
    -0.81
    hamento
    -0.81
     ewes
    -0.81
    Ngày
    -0.81
     Anima
    -0.80
     "");
    -0.80
     pyrite
    -0.80
    POSITIVE LOGITS
     fish
    1.70
     crab
    1.47
     crabs
    1.32
     shrimp
    1.26
    fish
    1.13
    crab
    1.09
     starfish
    1.06
     jellyfish
    1.02
     shells
    1.01
     sharks
    1.01
    Activations Density 0.029%

    No Known Activations