© 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. 128012
    Prev
    Next
    INDEX
    Explanations

    medical suffixes (-al, -ar, -tic)

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

    medical anatomical terms with suffixes like "ual", "bar", "tic", and "mal" in medical/scientific text.

    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
     pensando
    -1.52
     minimalista
    -1.38
    カッコ
    -1.35
     isang
    -1.34
     dará
    -1.33
    樁
    -1.31
    乡
    -1.31
    开玩笑
    -1.30
        
    -1.30
    色んな
    -1.28
    POSITIVE LOGITS
     on
    1.53
     Mereka
    1.51
    مدیر
    1.50
    彣
    1.46
    this
    1.45
     їх
    1.44
    عالی
    1.43
    فقط
    1.41
    Приготовление
    1.41
    This
    1.41
    Activations Density 0.166%

    No Known Activations