© 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. 119747
    Prev
    Next
    INDEX
    Explanations

    by: [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
     ر
    -0.06
    一個
    -0.06
    single
    -0.06
     pihak
    -0.06
     پ
    -0.06
    Single
    -0.06
     პ
    -0.06
     並
    -0.05
     上
    -0.05
     సంవ
    -0.05
    POSITIVE LOGITS
     എല്ലാ
    0.07
     those
    0.07
    sby
    0.07
     the
    0.07
     all
    0.07
    IDGE
    0.07
    adto
    0.06
     santa
    0.06
    依靠
    0.06
     everlasting
    0.06
    Activations Density 0.003%

    No Known Activations