© 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. 10-GEMMASCOPE-RES-131K
    7. 99016
    Prev
    Next
    INDEX
    Explanations

    catalyze enzymes

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

    enzyme catalytic terminology, particularly detecting words like "catalyzes" and foreign language words ending in "eze" or "ina".

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

    The neuron fires on tokens from non-English words that include accented or special (non-ASCII) characters.

    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
    ↵↵
    -2.33
    ).
    -2.14
    ",
    -2.05
     '
    -1.91
    
    -1.82
    ...
    -1.80
    および
    -1.80
    ("")]
    -1.78
    and
    -1.77
    ...)
    -1.77
    POSITIVE LOGITS
    觏
    2.41
    ་་
    2.36
    踯
    2.33
    iſter
    2.03
    Ꮠ
    2.00
    lüssel
    1.95
    荭
    1.84
    ~”
    1.83
    泚
    1.83
    actéristi
    1.82
    Activations Density 0.001%

    No Known Activations