© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34715
    Prev
    Next
    INDEX
    Explanations

    di-tert-butyl

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

    chemical compound names and chemical structure notations.

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

    The neuron fires on numeric tokens (especially digits in chemical names or other technical numeric references).

    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
     transfusion
    -0.84
    Emerson
    -0.84
     Strö
    -0.83
     Tutto
    -0.78
     muta
    -0.78
     SFP
    -0.75
     DESCRIPT
    -0.74
     ничего
    -0.74
     Gj
    -0.74
    urlpatterns
    -0.72
    POSITIVE LOGITS
    тє
    0.77
     tertiary
    0.77
     branched
    0.77
    嚏
    0.77
     hindered
    0.75
    lığı
    0.72
     umożli
    0.71
     Jacoby
    0.70
     bulky
    0.70
    rit
    0.70
    Activations Density 0.075%

    No Known Activations