© 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. 121065
    Prev
    Next
    INDEX
    Explanations

    including other languages

    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
     βασ
    -0.06
     nDims
    -0.06
    她
    -0.06
    他們
    -0.05
    他们
    -0.05
    ılmış
    -0.05
     निभाने
    -0.05
    鋰
    -0.05
    কর্ণ
    -0.05
     weil
    -0.05
    POSITIVE LOGITS
     including
    0.08
     termasuk
    0.07
     включая
    0.07
     včetně
    0.07
     хотя
    0.07
    टेस्ट
    0.06
     includes
    0.06
     פר
    0.06
     gồm
    0.06
     at
    0.06
    Activations Density 0.001%

    No Known Activations