© 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. 116886
    Prev
    Next
    INDEX
    Explanations

    publication and access

    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
     weiteren
    -0.08
     不需要
    -0.07
     находи
    -0.07
     Aufgaben
    -0.07
     तहत
    -0.07
     Memories
    -0.07
     esposa
    -0.07
     soweit
    -0.07
     někter
    -0.07
    NumberOperation
    -0.07
    POSITIVE LOGITS
     dissemination
    0.07
    new
    0.06
     disseminate
    0.06
    read
    0.05
     আপডেট
    0.05
     specialists
    0.05
    随时
    0.05
    読む
    0.05
     –
    0.05
     accessing
    0.05
    Activations Density 0.002%

    No Known Activations