© 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. 3359
    Prev
    Next
    INDEX
    Explanations

    disadvantages

    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
    στή
    0.70
    栩
    0.69
    ൽപ്പ
    0.65
     adequacy
    0.63
     thao
    0.63
    injlim
    0.63
    chehen
    0.63
     squire
    0.63
    ান্ড
    0.62
    侥
    0.62
    POSITIVE LOGITS
     negative
    2.30
    Negative
    2.23
     Negative
    2.15
     negatives
    2.15
     negativo
    2.07
     negatif
    2.07
     negativas
    2.05
     downsides
    2.01
    negative
    1.98
     negativ
    1.96
    Activations Density 1.295%

    No Known Activations