© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2385
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ☎
    0.81
    Telephone
    0.77
    견
    0.77
     Biotechnol
    0.76
    を紹介
    0.75
    ducation
    0.75
    reux
    0.74
    ার্জন
    0.74
    סק
    0.73
    ℡
    0.73
    POSITIVE LOGITS
     texting
    1.03
     Haiti
    1.02
     امد
    1.02
     donations
    1.00
     Crisis
    1.00
     messaging
    0.96
     Hamas
    0.95
    Crisis
    0.94
     lifeboat
    0.94
     donated
    0.92
    Activations Density 0.511%

    No Known Activations