© 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. 3126
    Prev
    Next
    INDEX
    Explanations

    fish and sardines

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

    scientific names of fish and other aquatic species.

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

    The neuron is strongly activated by scientific taxonomic and classification terms (Latin genus/species names, taxonomic ranks, and related headings).

    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
    牡蠣
    -0.96
     coyote
    -0.86
    Cattle
    -0.81
    propy
    -0.80
     koala
    -0.77
     cocoa
    -0.76
     Cattle
    -0.75
    Koala
    -0.75
    obab
    -0.73
     zaken
    -0.72
    POSITIVE LOGITS
     fish
    4.50
    fish
    3.27
    Fish
    3.20
     Fish
    3.06
     fishes
    2.78
    鱼
    2.70
     FISH
    2.56
    魚
    2.56
    🐟
    2.53
    FISH
    2.44
    Activations Density 0.154%

    No Known Activations