© 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. 45233
    Prev
    Next
    INDEX
    Explanations

    matrix metalloproteinase

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

    technical or scientific terminology, particularly words like "metalloproteinases," "traumatized," and specialized terms across different languages.

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

    The neuron is tuned to pick out specialized multi-syllable terms—especially scientific or technical words built on Greek or Latin roots.

    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
     creepy
    -2.72
    
    -2.48
    떳
    -2.48
    弱点
    -2.42
     Öffnen
    -2.38
    辄
    -2.33
    挈
    -2.33
    在那里
    -2.33
     pf
    -2.30
     Änderungen
    -2.30
    POSITIVE LOGITS
    e
    3.05
    l
    2.92
    葙
    2.81
    </strong>
    2.80
    this
    2.67
     juft
    2.58
    t
    2.50
    而不
    2.42
    and
    2.30
     lakini
    2.27
    Activations Density 0.021%

    No Known Activations