© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129079
    Prev
    Next
    INDEX
    Explanations

    html id attributes

    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
     blogging
    -0.06
     storing
    -0.06
     sẽ
    -0.06
     will
    -0.06
     tomorrow
    -0.06
    🎓
    -0.06
    entation
    -0.06
    と思う
    -0.06
     moving
    -0.05
     wal
    -0.05
    POSITIVE LOGITS
    ontaneous
    0.06
     Proposed
    0.06
    即
    0.06
     სპეცი
    0.06
    密
    0.06
    EVERY
    0.06
     Sikkim
    0.06
    irti
    0.06
    certain
    0.05
     mágico
    0.05
    Activations Density 0.007%

    No Known Activations