© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118492
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     apologize
    -0.07
     ঔ
    -0.07
    methods
    -0.06
     terlebih
    -0.06
     OECD
    -0.06
     apologise
    -0.06
    خواهد
    -0.06
     procédés
    -0.06
     apologized
    -0.06
    法的
    -0.06
    POSITIVE LOGITS
     youths
    0.07
     some
    0.06
    ikir
    0.06
     youth
    0.06
     পূর্বা
    0.06
     контак
    0.06
     sixty
    0.06
    講座
    0.06
     vulnerable
    0.05
     restricting
    0.05
    Activations Density 0.000%

    No Known Activations