© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64391
    Prev
    Next
    INDEX
    Explanations

    GRACE gravity studies

    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_34/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
    ladores
    -0.81
     broke
    -0.80
    ずれ
    -0.77
    Predecesor
    -0.76
     Toxicological
    -0.73
    ᥙ
    -0.71
     develop
    -0.71
    OPHER
    -0.70
    搶
    -0.69
     transposition
    -0.69
    POSITIVE LOGITS
     GRACE
    1.26
     Gravity
    1.17
    Gravity
    1.10
    GRACE
    1.10
     SWOT
    0.90
     gravity
    0.89
     JPL
    0.85
     grav
    0.82
    GRAV
    0.81
    grace
    0.81
    Activations Density 0.009%

    No Known Activations