© 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. 118333
    Prev
    Next
    INDEX
    Explanations

    or means

    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
    omel
    -0.07
     علاج
    -0.06
     chyba
    -0.06
     когда
    -0.06
    Prevent
    -0.06
    楠
    -0.06
    の日
    -0.06
     दैनिक
    -0.06
    тан
    -0.05
     تاريخ
    -0.05
    POSITIVE LOGITS
    न्यास
    0.06
    延伸
    0.06
     reptile
    0.06
    ᵢ
    0.06
     enticing
    0.06
     nominees
    0.06
     truncation
    0.06
    戛
    0.06
    어를
    0.06
     significado
    0.06
    Activations Density 0.072%

    No Known Activations