© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73455
    Prev
    Next
    INDEX
    Explanations

    ambulatory medical contexts

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

    legal and technical terms related to document processes like "redress," "vend," "embossing," and medical terms like "ambulatory."

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

    This neuron fires on content words that contain adjacent consonant clusters (e.g. “mb,” “ss,” “nd,” “br,” etc.).

    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
    3
    -3.31
     {
    -3.19
    <b>
    -2.77
     \
    -2.67
     
    -2.58
    2
    -2.56
    5
    -2.55
     

    -2.53
    8
    -2.47
    i
    -2.39
    POSITIVE LOGITS
    镦
    2.98
     ferrovia
    2.92
     内衣
    2.72
    ⼥
    2.72
     merav
    2.70
    ╽
    2.69
     saluti
    2.67
     banyo
    2.61
     dirit
    2.56
     animali
    2.55
    Activations Density 0.005%

    No Known Activations