© 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. 128047
    Prev
    Next
    INDEX
    Explanations

    needed items

    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
     pomocí
    -0.08
     usando
    -0.07
     using
    -0.07
     sambil
    -0.06
    selecting
    -0.06
     empowering
    -0.06
     pilih
    -0.06
     используя
    -0.06
     kullanarak
    -0.06
     પછી
    -0.06
    POSITIVE LOGITS
     needed
    0.08
     whose
    0.07
     kommer
    0.07
     for
    0.07
     will
    0.07
     supplémentaires
    0.07
     wraz
    0.07
    用於
    0.06
     diperlukan
    0.06
     Needed
    0.06
    Activations Density 0.008%

    No Known Activations