© 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. 12224
    Prev
    Next
    INDEX
    Explanations

    Mytilus and mollusks

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

    This neuron identifies taxonomic descriptions of marine mollusks, particularly focusing on the scientific names and classifications of species like snails, mussels, and bivalves.

    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
    ÑOS
    -0.77
     coyote
    -0.74
     rattan
    -0.70
    Opts
    -0.69
    鯖
    -0.69
    Milo
    -0.68
     werewolf
    -0.67
     perine
    -0.67
    Kav
    -0.66
    }}.
    -0.66
    POSITIVE LOGITS
     shells
    1.80
     shell
    1.73
    shell
    1.61
    Shell
    1.45
     clams
    1.44
    貝
    1.39
     shelled
    1.38
     oysters
    1.38
     clam
    1.38
     mussel
    1.34
    Activations Density 0.066%

    No Known Activations