© 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. 10-GEMMASCOPE-RES-131K
    7. 129714
    Prev
    Next
    INDEX
    Explanations

    amphibian, oomycete, mites

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

    names of amphibians and reptiles, such as newts, salamanders, and frogs.

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

    The neuron detects Latin taxonomic names of amphibian genera and species.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    轳
    -2.72
    傒
    -2.63
    鵙
    -2.50
    attutto
    -2.38
     zoude
    -2.27
    ཥ
    -2.20
    
    -2.19
    鹇
    -2.17
    
    -2.17
    ientras
    -2.16
    POSITIVE LOGITS
    ↵↵
    2.22
    \
    2.16
    Generally
    2.08
    Shortly
    2.05
    Usually
    2.03
    Surprisingly
    2.02
    M
    2.02
    Through
    2.02
    Four
    1.96
    Ironically
    1.96
    Activations Density 0.008%

    No Known Activations