© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56979
    Prev
    Next
    INDEX
    Explanations

    synthesized, prepared, esterification

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

    scientific terminology in chemistry and biochemistry research papers.

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

    The neuron strongly activates on past-tense or passive-voice verbs (e.g. “were separated,” “was prepared,” “identified,” “obtained”).

    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
    TestFixture
    -0.94
     劇場
    -0.93
     berbicara
    -0.93
    DATABASES
    -0.89
    研发
    -0.88
    ÇÕES
    -0.86
     презента
    -0.86
     nanoparticle
    -0.85
     Zombie
    -0.85
     membuat
    -0.84
    POSITIVE LOGITS
    authentic
    0.99
     infrar
    0.95
     cristales
    0.94
    ဂ
    0.94
    NFT
    0.91
     Scrolls
    0.91
    jø
    0.90
    ICY
    0.90
     cápsulas
    0.90
     authentic
    0.89
    Activations Density 0.117%

    No Known Activations