© 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. 3305
    Prev
    Next
    INDEX
    Explanations

    words starting with Em

    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
     cercano
    1.00
    롯
    0.99
    ॉर्डिंग
    0.98
     killer
    0.96
    UAGES
    0.94
    arrayList
    0.91
     hutan
    0.91
    瑣
    0.91
     combed
    0.90
     harassing
    0.89
    POSITIVE LOGITS
    ballage
    1.21
    urgo
    1.19
    fehlung
    1.19
    fohlen
    1.09
     EMP
    1.04
    assy
    1.01
     vesicle
    1.01
    em
    1.00
    merich
    0.99
     Noether
    0.99
    Activations Density 0.183%

    No Known Activations