© 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. 3416
    Prev
    Next
    INDEX
    Explanations

    multilingual context descriptions

    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
     clockRadius
    1.18
     phthal
    1.07
    ರ್ಷ
    1.07
    ➨
    1.04
     undercut
    1.03
     indefinitely
    1.02
     autocorrelation
    1.01
    ァ
    1.01
     而且
    1.01
     griseo
    1.00
    POSITIVE LOGITS
     pasal
    1.14
    ございます
    1.02
     ges
    0.93
    harga
    0.93
    ura
    0.92
    ի
    0.91
     Ekonomi
    0.91
    ী
    0.90
     adjour
    0.90
     العلوم
    0.90
    Activations Density 0.000%

    No Known Activations