© 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. 130179
    Prev
    Next
    INDEX
    Explanations

    names after first name

    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
     suna
    -0.06
    🎼
    -0.06
     sogenannte
    -0.06
     with
    -0.06
     cantidades
    -0.06
     употреб
    -0.06
     molecules
    -0.06
     without
    -0.06
    같이
    -0.05
    basics
    -0.05
    POSITIVE LOGITS
     potwier
    0.07
     you
    0.07
     epidemiology
    0.07
     ((
    0.06
     (\
    0.06
     mendukung
    0.06
     confirmar
    0.06
     подтвер
    0.06
     confirm
    0.06
     conferma
    0.06
    Activations Density 0.010%

    No Known Activations