© 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. 72218
    Prev
    Next
    INDEX
    Explanations

    court citations and legal districts

    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
    珦
    -2.05
    甭
    -1.77
     этой
    -1.73
    」,
    -1.60
     هنا
    -1.51
     этом
    -1.47
    ᩠
    -1.45
    VERTISING
    -1.45
     soigneusement
    -1.44
     auténtica
    -1.42
    POSITIVE LOGITS
     by
    1.83
    .
    1.66
     on
    1.63
     but
    1.63
     in
    1.55
     the
    1.50
     both
    1.44
    renowned
    1.44
     even
    1.39
     prominent
    1.35
    Activations Density 0.007%

    No Known Activations