© 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. 103572
    Prev
    Next
    INDEX
    Explanations

    trophic effects

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

    scientific terms with the suffix "-trophic" or "-copic" related to biological and medical terminology.

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

    The neuron activates on words ending in the adjectival suffix “-ic.”

    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
     we
    -2.77
     '';
    -2.73
    ?
    -2.48
     deliciously
    -2.38
    𐄁
    -2.36
    ت
    -2.33
     adorned
    -2.30
    ༷
    -2.30
     AMAZING
    -2.28
    黑衣
    -2.28
    POSITIVE LOGITS
    目前的
    2.61
     increases
    2.56
    钲
    2.55
     onResponse
    2.48
    Only
    2.47
    Without
    2.44
    émy
    2.41
    屃
    2.41
     That
    2.39
     achieving
    2.38
    Activations Density 0.157%

    No Known Activations