© 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. 15697
    Prev
    Next
    INDEX
    Explanations

    INT data types or abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ݯ
    -2.63
    乆
    -2.56
    ે
    -2.52
    Their
    -2.52
    ↵↵
    -2.50
     ”
    -2.45
    ,’
    -2.22
     какую
    -2.22
    }$
    -2.19
     worin
    -2.19
    POSITIVE LOGITS
     '
    2.72
     vitally
    2.55
     Even
    2.50
    。"
    2.50
     Although
    2.45
     suggests
    2.42
     Despite
    2.42
    𖡼
    2.31
     africain
    2.31
     supremely
    2.28
    Activations Density 0.002%

    No Known Activations