© 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. 117030
    Prev
    Next
    INDEX
    Explanations

    Q: A

    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
     Archim
    -0.06
               
    -0.06
    ステンレス
    -0.06
    getResource
    -0.06
    ēj
    -0.06
    дру
    -0.06
     odlič
    -0.06
     anderes
    -0.06
    цвет
    -0.06
     autre
    -0.06
    POSITIVE LOGITS
     tormented
    0.07
     bearish
    0.07
    👶
    0.06
     leftmost
    0.06
     اولین
    0.06
     створи
    0.06
     അവൻ
    0.06
     आफ्नो
    0.06
     GLA
    0.06
    embry
    0.06
    Activations Density 0.001%

    No Known Activations