© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 129748
    Prev
    Next
    INDEX
    Explanations

    file paths and identifiers

    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
     inicia
    -0.07
     trong
    -0.07
     في
    -0.06
     molte
    -0.06
     in
    -0.06
     muchos
    -0.06
     votre
    -0.06
     nombreuses
    -0.06
     viele
    -0.06
     иногда
    -0.06
    POSITIVE LOGITS
     כך
    0.06
     både
    0.06
     지금까지
    0.06
     committees
    0.06
     both
    0.06
    ována
    0.06
    上也
    0.05
    ட்டால்
    0.05
     flip
    0.05
     대하여
    0.05
    Activations Density 0.001%

    No Known Activations