© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1544
    Prev
    Next
    INDEX
    Explanations

    aquarium fish and environments

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

    information related to fish species and aquatic animals.

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

    The neuron strongly activates on lines that name or label a defined term or heading—e.g. glossary entries, species names, taxonomic or section headers.

    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
    護士
    -0.84
     silicon
    -0.77
     materials
    -0.77
     silicone
    -0.77
    brania
    -0.75
    廝
    -0.75
    ⁞
    -0.75
    żdy
    -0.73
    <0xCE>
    -0.72
     substances
    -0.72
    POSITIVE LOGITS
     Require
    0.91
    requ
    0.90
    Requ
    0.90
     Requ
    0.88
    Suggested
    0.84
     temperament
    0.83
     Tank
    0.83
    μβρίου
    0.83
    suggestions
    0.82
    colgroup
    0.81
    Activations Density 0.013%

    No Known Activations