© 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. 114045
    Prev
    Next
    INDEX
    Explanations

    acronyms and technical terms

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

    acronyms and abbreviations in technical, medical, or formal contexts.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
    Negative Logits
    नलोड
    -2.89
    鐿
    -2.58
    鵟
    -2.42
    </h4>
    -2.39
    ）：
    -2.38
    梠
    -2.38
    
    -2.34
    migiano
    -2.34
    
    -2.34
    鈇
    -2.28
    POSITIVE LOGITS
     خلال
    2.66
    of
    2.55
    </i>
    2.55
    '
    2.45
     et
    2.41
    s
    2.31
    小孩子
    2.25
     Hinblick
    2.25
     ambayo
    2.23
    ين
    2.20
    Activations Density 0.028%

    No Known Activations