© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113357
    Prev
    Next
    INDEX
    Explanations

    following "the" with legal acts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ........
    -1.68
     .......
    -1.66
     .........
    -1.64
     -"
    -1.62
    titial
    -1.59
    ᥬ
    -1.58
    甗
    -1.53
    があり
    -1.52
     premières
    -1.48
     černé
    -1.46
    POSITIVE LOGITS
     of
    2.17
     both
    2.16
    ↵
    1.88
     they
    1.86
     that
    1.85
     it
    1.73
     stated
    1.73
     兩
    1.67
     relatively
    1.64
     each
    1.63
    Activations Density 0.091%

    No Known Activations