© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90229
    Prev
    Next
    INDEX
    Explanations

    endemic species or location

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

    phrases indicating that a species is endemic to a specific geographic location.

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

    The neuron strongly responds to taxonomic description passages—especially “is a species of …” statements and “endemic to [location]” distribution phrases.

    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
    Estate
    -0.81
    Episode
    -0.81
    ésult
    -0.78
     Carly
    -0.75
    Egy
    -0.73
     Boer
    -0.73
    تج
    -0.71
    Categories
    -0.70
     Mourinho
    -0.70
    wohnung
    -0.69
    POSITIVE LOGITS
     endemic
    4.97
     ende
    3.03
    ende
    2.91
     End
    2.83
     эн
    2.34
    End
    2.33
     END
    2.25
     ен
    1.91
     Ende
    1.89
    ENDE
    1.87
    Activations Density 0.181%

    No Known Activations