© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1904
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     bru
    0.73
     ret
    0.70
     ador
    0.67
     Flask
    0.66
     แก
    0.65
     服
    0.64
     Brian
    0.63
     MOD
    0.63
    Â
    0.62
    巧妙
    0.61
    POSITIVE LOGITS
    可能な
    0.96
    らえる
    0.78
    PropertySheets
    0.77
    вт
    0.76
    முதல்
    0.76
    тып
    0.76
    çons
    0.75
    栦
    0.75
     {|
    0.75
    沆
    0.75
    Activations Density 0.421%

    No Known Activations