© 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. 130198
    Prev
    Next
    INDEX
    Explanations

    data types and keywords

    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
    杍
    -0.06
     وغيرها
    -0.06
     etc
    -0.06
     وغير
    -0.06
     相关
    -0.06
     முதலிய
    -0.06
     pressed
    -0.05
    దీ
    -0.05
    withId
    -0.05
    Види
    -0.05
    POSITIVE LOGITS
     obtenir
    0.06
     गर
    0.06
     Disturb
    0.06
     hogy
    0.06
     farther
    0.06
    撹
    0.05
     Khark
    0.05
     qīng
    0.05
     tranquille
    0.05
     лютого
    0.05
    Activations Density 0.010%

    No Known Activations