© 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. 31-GEMMASCOPE-2-RES-262K
    7. 199665
    Prev
    Next
    INDEX
    Explanations

    generating sequences like abc

    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_31_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
     disagrees
    0.47
     riguardo
    0.44
    =
    0.43
    :
    0.41
    تون
    0.40
     obi
    0.39
     dépasse
    0.38
    ovu
    0.38
    ிட்டு
    0.37
     OFF
    0.37
    POSITIVE LOGITS
    kten
    0.53
    ərd
    0.53
     বৃষ্টির
    0.52
     વરસાદ
    0.50
     انکار
    0.50
     Caed
    0.50
     도시
    0.49
    𝗯
    0.49
     desarrollan
    0.49
    confirmed
    0.48
    Activations Density 0.006%

    No Known Activations