© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 9004
    Prev
    Next
    INDEX
    Explanations

    p-value and significance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    correlation
    0.64
     correlation
    0.59
    Correlation
    0.54
     रिलेशनशिप
    0.52
    溇
    0.52
     correlations
    0.51
     Correlations
    0.51
    correlated
    0.50
     uncorrelated
    0.47
     correlated
    0.47
    POSITIVE LOGITS
     Significance
    1.09
     significance
    1.05
     p
    0.88
     signific
    0.71
    p
    0.67
     Signific
    0.66
     alpha
    0.64
     FDR
    0.64
     reject
    0.63
     test
    0.62
    Activations Density 0.007%

    No Known Activations