Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 11258
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    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
    节目
    0.66
    ोनेशिया
    0.64
    伥
    0.62
    基础设施
    0.61
    豪华
    0.61
    ysław
    0.61
    🌮
    0.61
     服务
    0.61
    newToken
    0.60
    ępu
    0.59
    POSITIVE LOGITS
     statistical
    1.37
     ANOVA
    1.30
     Statistical
    1.22
     Bayesian
    1.17
     nonparametric
    1.10
     statistically
    1.08
    statistical
    1.07
     bivariate
    1.05
     SPSS
    1.03
    ivariate
    1.00
    Activations Density 0.242%

    No Known Activations