© 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. 117988
    Prev
    Next
    INDEX
    Explanations

    size

    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
     illiterate
    -0.05
     miércoles
    -0.05
     varies
    -0.05
    №
    -0.05
    കൻ
    -0.05
     држа
    -0.05
     আশে
    -0.05
     dilute
    -0.05
    Sw
    -0.05
     charities
    -0.05
    POSITIVE LOGITS
     najbol
    0.07
     기능을
    0.07
     plywood
    0.06
     nutzen
    0.06
     remarked
    0.06
     genutzt
    0.06
    ovanie
    0.06
    可以通过
    0.06
    青山
    0.06
    ondere
    0.06
    Activations Density 0.001%

    No Known Activations