© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 32301
    Prev
    Next
    INDEX
    Explanations

    numbers and days

    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
     complementing
    0.38
    錢
    0.37
    同樣
    0.36
     १००
    0.36
    男友
    0.36
    衣服
    0.35
     پولیس
    0.35
    篝
    0.35
     समान
    0.35
    墅
    0.35
    POSITIVE LOGITS
     Tuesdays
    0.82
    Tuesday
    0.82
     Tuesday
    0.79
     seventeen
    0.71
     seventeenth
    0.67
     Aunt
    0.66
     seventh
    0.65
     purple
    0.65
     Wednesdays
    0.64
     tuesday
    0.64
    Activations Density 0.055%

    No Known Activations