© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10488
    Prev
    Next
    INDEX
    Explanations

    SQL SELECT FROM clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
    俊
    0.72
    Zu
    0.71
    AddItem
    0.70
    Combine
    0.68
     ermög
    0.68
    Gi
    0.67
     डायरे
    0.66
    ها
    0.65
    ″]
    0.64
    Num
    0.64
    POSITIVE LOGITS
    ंटा
    0.90
     aware
    0.79
     mediators
    0.75
    roft
    0.74
     quadrants
    0.72
    ิง
    0.72
     second
    0.71
     guys
    0.71
    னமாக
    0.71
     instal
    0.70
    Activations Density 0.055%

    No Known Activations