© 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. 11720
    Prev
    Next
    INDEX
    Explanations

    recent past action

    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
     eventual
    0.45
     eventually
    0.41
     subsequent
    0.40
    ┑
    0.39
    Eventually
    0.39
     দিতেন
    0.39
     Eventually
    0.39
     occasional
    0.39
     Subsequent
    0.38
     প্রচলিত
    0.38
    POSITIVE LOGITS
    刚刚
    1.33
     recently
    1.25
    剛剛
    1.13
     недавно
    1.11
    recently
    1.11
     recientemente
    1.09
     appena
    1.07
    Recently
    1.04
    刚
    1.04
     freshly
    1.03
    Activations Density 0.012%

    No Known Activations