© 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. 40-GEMMASCOPE-2-RES-65K
    7. 3965
    Prev
    Next
    INDEX
    Explanations

    daily and weekly regularity

    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_65k_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
     occasionally
    0.45
     Occasionally
    0.43
     anytime
    0.41
     আগেই
    0.41
    티
    0.40
    illant
    0.39
    随时
    0.39
    Ти
    0.38
    Occasionally
    0.38
    时
    0.38
    POSITIVE LOGITS
     throughout
    0.63
     regularity
    0.58
     протягом
    0.57
     routine
    0.53
     протяжении
    0.53
     regolare
    0.49
     tijekom
    0.48
     Throughout
    0.47
     rutina
    0.47
     Routine
    0.46
    Activations Density 0.135%

    No Known Activations