© 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. 116603
    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
     lahko
    -0.06
     dieci
    -0.06
     lacking
    -0.06
     خانه
    -0.06
     kasnije
    -0.06
    ώνει
    -0.06
     kanilang
    -0.06
     डांस
    -0.06
     maakte
    -0.06
     nineteen
    -0.06
    POSITIVE LOGITS
     visionary
    0.07
     செயல்படுத்த
    0.06
    🌙
    0.06
     TH
    0.06
     physiology
    0.06
     componentes
    0.06
     observable
    0.06
     PH
    0.06
     nighttime
    0.06
     observables
    0.06
    Activations Density 0.000%

    No Known Activations