© 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. 117515
    Prev
    Next
    INDEX
    Explanations

    Reynolds number ratio

    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
     poveć
    -0.06
    ophyllum
    -0.06
     remodeled
    -0.06
     GWAS
    -0.06
     Symbols
    -0.06
     improved
    -0.06
     wonderful
    -0.06
     AMAZING
    -0.06
     thous
    -0.06
    ล็
    -0.06
    POSITIVE LOGITS
    eração
    0.06
     একের
    0.06
     basse
    0.06
     पुरी
    0.06
     contact
    0.06
     interacting
    0.06
    炰
    0.06
    ද්
    0.06
    irsi
    0.06
     অবস্থা
    0.05
    Activations Density 0.006%

    No Known Activations