© 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. 117196
    Prev
    Next
    INDEX
    Explanations

    medical, chemical, and scientific terms

    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
     그
    -0.06
     nisu
    -0.06
     ঘোষণার
    -0.06
     producto
    -0.06
    無論
    -0.06
    ㅠㅠ
    -0.06
     הוא
    -0.06
     McF
    -0.06
     ini
    -0.05
     mye
    -0.05
    POSITIVE LOGITS
    和大
    0.07
     इनको
    0.06
     डिजाइन
    0.06
     Needs
    0.06
     ভ্যাক
    0.06
     seznam
    0.06
     பல்கலை
    0.06
     vilken
    0.06
    意外
    0.06
    PerTrial
    0.05
    Activations Density 0.004%

    No Known Activations