© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11258
    Prev
    Next
    INDEX
    Explanations

    statistical

    np_acts-logits-general · gemini-2.5-flash-lite

    statistical analysis and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    钞
    0.62
    ysław
    0.61
     সড়ক
    0.59
    货物
    0.59
    骑士
    0.59
    节目
    0.57
     연료
    0.57
    💵
    0.57
    cèle
    0.56
    诗人
    0.56
    POSITIVE LOGITS
     statistical
    1.41
     ANOVA
    1.38
     nonparametric
    1.27
     Statistical
    1.24
    statistical
    1.21
     statist
    1.20
     statistically
    1.15
     bivariate
    1.14
     statistic
    1.12
     Bayesian
    1.11
    Activations Density 0.049%

    No Known Activations