© 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. 607
    Prev
    Next
    INDEX
    Explanations

    word continuations

    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
     self
    0.90
     be
    0.88
     using
    0.75
     fashion
    0.74
     pack
    0.71
     used
    0.69
     relay
    0.68
     game
    0.68
     take
    0.68
    !
    0.68
    POSITIVE LOGITS
    ੲ
    1.05
    Ꮙ
    1.04
    <unused1710>
    1.01
    метров
    1.01
    Rit
    1.01
    өнья
    0.99
    Benzoimidazole
    0.98
    खनऊ
    0.98
    MenuItemView
    0.98
    airie
    0.94
    Activations Density 0.776%

    No Known Activations