© 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. 10310
    Prev
    Next
    INDEX
    Explanations

    https links or citations

    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
    ,]
    1.05
    ](/
    1.03
    )]
    1.01
    ](
    0.98
    ](#
    0.95
     Aqui
    0.94
     potentialities
    0.91
    ](./
    0.89
    aise
    0.89
    യ്ക്ക്
    0.87
    POSITIVE LOGITS
    ਾਰ
    0.88
    ారు
    0.77
    需要在
    0.75
    ナー
    0.75
    ős
    0.73
    整数
    0.72
    струк
    0.71
    ening
    0.71
    িলম্বে
    0.70
     databases
    0.70
    Activations Density 0.041%

    No Known Activations