© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128007
    Prev
    Next
    INDEX
    Explanations

    value: or =

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    set
    -0.06
     localizada
    -0.06
     Helper
    -0.06
     ሲ
    -0.06
    Helper
    -0.06
    一番
    -0.05
    ven
    -0.05
     doğru
    -0.05
    次方
    -0.05
    といえば
    -0.05
    POSITIVE LOGITS
    因為
    0.07
     Farb
    0.07
    因为
    0.06
     ờ
    0.06
     likely
    0.06
     Toxicol
    0.06
     احتم
    0.06
     begg
    0.06
    )(((
    0.06
     從
    0.06
    Activations Density 0.016%

    No Known Activations