© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 120737
    Prev
    Next
    INDEX
    Explanations

    team and we

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Bary
    -0.06
     शैल
    -0.06
     சுமார்
    -0.06
    typically
    -0.06
    役割
    -0.06
    确保
    -0.06
    typical
    -0.05
    average
    -0.05
     that
    -0.05
     সুরক্ষিত
    -0.05
    POSITIVE LOGITS
     diverse
    0.06
     diferite
    0.06
     გან
    0.06
    繋がり
    0.06
    つなが
    0.06
     ehm
    0.06
    _{-}^{
    0.06
     interdependent
    0.06
    ————————————————
    0.06
     😄
    0.06
    Activations Density 0.008%

    No Known Activations