© 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. 120789
    Prev
    Next
    INDEX
    Explanations

    configuration files

    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
     জানতে
    -0.06
    ermos
    -0.06
    创新
    -0.06
    okon
    -0.06
     такое
    -0.06
     रज
    -0.06
     международ
    -0.06
     '/
    -0.06
     neues
    -0.06
    进一步
    -0.05
    POSITIVE LOGITS
     repairs
    0.06
    getVersion
    0.06
     Foundation
    0.06
    をはじめ
    0.06
    aunque
    0.06
     Liga
    0.06
     replacement
    0.06
     Munich
    0.06
     replaced
    0.06
     Patrick
    0.06
    Activations Density 0.004%

    No Known Activations