© 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. 58119
    Prev
    Next
    INDEX
    Explanations

    words starting with Gal

    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
    ſhip
    -2.72
    哢
    -2.67
    $\$$
    -2.58
    塍
    -2.55
     INGRED
    -2.53
    逦
    -2.52
    缺点
    -2.48
    毉
    -2.48
    攆
    -2.45
    所需的
    -2.44
    POSITIVE LOGITS
    "
    3.13
    2
    3.03
    ’
    2.94
     the
    2.77
    )
    2.69
     {
    2.44
    ia
    2.38
        
    2.38
    en
    2.34
     Your
    2.33
    Activations Density 0.015%

    No Known Activations