© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59541
    Prev
    Next
    INDEX
    Explanations

    stoichiometry

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

    The neuron identifies chemistry and scientific terms, particularly "stoichiometry" and related technical vocabulary.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    (
    -2.23
     prípade
    -2.08
     delve
    -2.06
     burgeoning
    -2.06
     Two
    -1.98
     Makes
    -1.96
     unwavering
    -1.95
    For
    -1.95
    そして
    -1.90
    Shortly
    -1.88
    POSITIVE LOGITS
    enumi
    2.41
    ates
    2.34
     they
    2.22
    が多く
    2.17
    がたくさん
    2.16
    鵙
    2.16
    沵
    2.13
    艄
    2.03
    まわり
    1.97
    ۔
    1.97
    Activations Density 0.001%

    No Known Activations