© 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. 128370
    Prev
    Next
    INDEX
    Explanations

    Polypharmacy

    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
     controvers
    -0.07
     notably
    -0.07
     Notably
    -0.06
     sepenuhnya
    -0.06
     वर्च
    -0.06
     purchased
    -0.06
     disputa
    -0.06
    inim
    -0.05
    鍑
    -0.05
     attempts
    -0.05
    POSITIVE LOGITS
     unconscious
    0.07
     otros
    0.06
    斡
    0.06
     ess
    0.06
    その他の
    0.06
    腐
    0.06
    firstName
    0.06
     firstname
    0.06
     Arias
    0.06
     Italians
    0.06
    Activations Density 0.002%

    No Known Activations