© 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. 116082
    Prev
    Next
    INDEX
    Explanations

    days shipping

    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
     says
    -0.07
    আজ
    -0.06
     geführt
    -0.06
     tạo
    -0.06
     भरे
    -0.05
     फ्लैट
    -0.05
    NSString
    -0.05
    گوید
    -0.05
     including
    -0.05
    樹脂
    -0.05
    POSITIVE LOGITS
     ноябре
    0.06
     ache
    0.06
     Bian
    0.06
     akong
    0.06
     Europe
    0.06
    jeeling
    0.06
     undangan
    0.06
     Diwali
    0.06
     redox
    0.06
     Ireland
    0.06
    Activations Density 0.002%

    No Known Activations