© 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. 22-GEMMASCOPE-RES-131K
    7. 33855
    Prev
    Next
    INDEX
    Explanations

    fish and marine life

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

    The neuron identifies species names and terminology related to marine organisms, particularly fish.

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

    The neuron is detecting scientific or taxonomic terms—especially Latin binomial names of fish and other organisms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     discrepan
    -1.39
     territ
    -1.38
     mision
    -1.37
     playera
    -1.36
     colore
    -1.34
    vidade
    -1.32
     fundas
    -1.32
     quarto
    -1.31
     seru
    -1.30
     fator
    -1.30
    POSITIVE LOGITS
    ִּ
    1.42
     ihrer
    1.40
    ärsk
    1.38
     seiner
    1.36
     spiegel
    1.35
    jük
    1.30
    ModelAdmin
    1.27
     säs
    1.27
     lachen
    1.20
    ֶּ
    1.20
    Activations Density 0.065%

    No Known Activations