© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3211
    Prev
    Next
    INDEX
    Explanations

    documentation links and ai urls

    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
    Negative Logits
    '/
    0.80
    society
    0.80
     pulgadas
    0.79
     kife
    0.78
     richard
    0.76
     Архів
    0.75
    
    0.75
    aacute
    0.74
     سنه
    0.72
    റ്റ്
    0.71
    POSITIVE LOGITS
    .
    0.77
     Fabric
    0.73
     Component
    0.69
     Shader
    0.68
     .
    0.65
     Dog
    0.65
     Pulse
    0.65
     Prototype
    0.65
     Glitter
    0.64
     Nodes
    0.64
    Activations Density 0.174%

    No Known Activations