© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23341
    Prev
    Next
    INDEX
    Explanations

    easy recipes

    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
    픕
    0.46
    гают
    0.41
     decayed
    0.39
    ək
    0.39
    कानेर
    0.38
    ético
    0.38
     distilling
    0.38
    罣
    0.38
     decaying
    0.37
    蝈
    0.37
    POSITIVE LOGITS
     easy
    1.08
     Easy
    0.98
     fácil
    0.98
     recipes
    0.98
    easy
    0.96
    Easy
    0.96
    簡単
    0.94
     EASY
    0.93
     Recipes
    0.90
     fáciles
    0.90
    Activations Density 0.007%

    No Known Activations