© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130753
    Prev
    Next
    INDEX
    Explanations

    word followed by word

    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
     blad
    -0.06
     QE
    -0.05
     нуля
    -0.05
     বৈধ
    -0.05
     inherently
    -0.05
    standing
    -0.05
     फैमिली
    -0.05
     خطر
    -0.05
    ////////
    -0.05
    ಊ
    -0.05
    POSITIVE LOGITS
     was
    0.07
     sebelumnya
    0.07
     იყო
    0.06
     pilih
    0.06
    bukti
    0.06
     позднее
    0.06
     sélectionner
    0.06
     seleccione
    0.06
     Energies
    0.06
     Estr
    0.06
    Activations Density 0.006%

    No Known Activations