© 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. 120140
    Prev
    Next
    INDEX
    Explanations

    chemistry formulas or symbols

    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
     তাঁদের
    -0.06
     arreg
    -0.06
     arreglo
    -0.06
    又
    -0.06
    sets
    -0.06
     επίσης
    -0.06
     ihrem
    -0.06
     Noël
    -0.06
    selecting
    -0.06
     ඔවුන්
    -0.06
    POSITIVE LOGITS
     Echin
    0.06
     brems
    0.06
     క్
    0.06
     ст
    0.06
    ეგის
    0.06
    orems
    0.06
    nze
    0.06
     કં
    0.06
     cows
    0.06
     والتي
    0.06
    Activations Density 0.001%

    No Known Activations