© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 6259
    Prev
    Next
    INDEX
    Explanations

    statistical significance and hypothesis testing

    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_40_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
    蛏
    0.52
     Cakes
    0.47
     оформления
    0.45
    沌
    0.45
    瓤
    0.44
    чке
    0.42
    带宽
    0.41
     рестора
    0.41
    गंगा
    0.41
    颍
    0.41
    POSITIVE LOGITS
     significance
    0.67
     Significance
    0.57
     statistical
    0.52
     signific
    0.49
     interpret
    0.47
     hypothesis
    0.44
    0
    0.44
     hypothes
    0.43
     hypotheses
    0.43
     hypothesized
    0.43
    Activations Density 0.006%

    No Known Activations