© 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. 118951
    Prev
    Next
    INDEX
    Explanations

    insert or 'new'

    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
     readjust
    -0.07
    change
    -0.07
     change
    -0.07
     trakcie
    -0.06
     changed
    -0.06
     during
    -0.06
     تغير
    -0.06
     конца
    -0.06
    During
    -0.06
     পুনরায়
    -0.06
    POSITIVE LOGITS
     similar
    0.07
    类似
    0.07
    similar
    0.06
     sánh
    0.06
     longues
    0.06
     sunny
    0.06
    類似
    0.06
     مثل
    0.06
     tomorrow
    0.06
     داریم
    0.06
    Activations Density 0.002%

    No Known Activations