© 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. 22-GEMMASCOPE-RES-131K
    7. 128068
    Prev
    Next
    INDEX
    Explanations

    The neuron flags numeric measurements and their associated units or reagent concentration specifications in scientific methods text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    buffers and chemical solutions

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

    chemical buffer solutions in scientific contexts.

    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_22/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
    PUTY
    -1.10
     Erfolgs
    -1.09
    inetics
    -1.08
     riesce
    -1.07
     jedna
    -1.04
     legte
    -1.00
    也算
    -1.00
     cartaz
    -0.99
    也不
    -0.98
     wondrous
    -0.98
    POSITIVE LOGITS
     with
    1.10
     vó
    1.09
    🔭
    1.04
    اسية
    1.02
    🍏
    1.02
     "),
    1.02
    dengan
    1.01
    ėjimo
    1.01
    isissez
    1.00
     हूं
    1.00
    Activations Density 0.012%

    No Known Activations