© 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. 120769
    Prev
    Next
    INDEX
    Explanations

    addresses and legal/official references

    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
     канторы
    -0.06
     গোলাবার
    -0.06
    另一
    -0.06
     பயன்படுத்த
    -0.06
     다른
    -0.06
     allows
    -0.06
    其它
    -0.06
     drugih
    -0.06
     modifies
    -0.06
     innych
    -0.05
    POSITIVE LOGITS
    aufs
    0.06
    おそらく
    0.06
    ículos
    0.06
     गलवान
    0.06
    也許
    0.06
    一定是
    0.06
     accurately
    0.06
     authoritative
    0.05
    legisl
    0.05
    釗
    0.05
    Activations Density 0.007%

    No Known Activations