© 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. 116023
    Prev
    Next
    INDEX
    Explanations

    phrases, numbers, abbreviations

    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
     ঘণ্টার
    -0.07
     případ
    -0.06
    则
    -0.06
    Ω
    -0.06
    则是
    -0.06
    ❔
    -0.06
    երը
    -0.05
     则
    -0.05
     upstate
    -0.05
    ቭ
    -0.05
    POSITIVE LOGITS
     này
    0.08
     esta
    0.07
     nenhuma
    0.07
     cette
    0.07
     هذه
    0.07
     এদিন
    0.07
     questa
    0.07
     tidak
    0.07
     этого
    0.07
     ৪
    0.07
    Activations Density 0.001%

    No Known Activations