© 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. 128294
    Prev
    Next
    INDEX
    Explanations

    continuation or status

    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
     grouping
    -0.06
     Catalogue
    -0.06
     রাজন
    -0.06
    什
    -0.06
    তুই
    -0.06
    清单
    -0.06
    सेल
    -0.06
     groupings
    -0.06
     Rush
    -0.05
     catalogue
    -0.05
    POSITIVE LOGITS
     συνεχ
    0.07
     ادامه
    0.07
    中の
    0.07
     selalu
    0.06
    contin
    0.06
     emulsion
    0.06
     SMALL
    0.06
     qualità
    0.06
     jpg
    0.06
     Contin
    0.06
    Activations Density 0.006%

    No Known Activations