© 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. 98469
    Prev
    Next
    INDEX
    Explanations

    sequence ending in return

    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
    犃
    0.55
    लोर
    0.44
     দেবযানী
    0.43
     Elovl
    0.41
     copyspace
    0.39
     erecting
    0.39
     obstáculos
    0.39
     ሽፋን
    0.39
     spooky
    0.38
    袢
    0.38
    POSITIVE LOGITS
    /*
    0.45
     gute
    0.42
     guten
    0.42
    га
    0.41
     buen
    0.41
     хоро
    0.41
    Good
    0.40
     why
    0.40
     le
    0.40
    i
    0.40
    Activations Density 0.002%

    No Known Activations