© 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. 117935
    Prev
    Next
    INDEX
    Explanations

    Code structure or list formatting

    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
     not
    -0.07
     Consultez
    -0.06
     需要
    -0.06
     on
    -0.06
    需要在
    -0.06
     बच
    -0.06
     rarely
    -0.06
     aching
    -0.06
     usually
    -0.06
    不但
    -0.06
    POSITIVE LOGITS
     cualquiera
    0.06
    allows
    0.06
     fatto
    0.06
     اسماء
    0.06
     وبالتالي
    0.06
     idx
    0.06
     إذا
    0.06
     consequências
    0.06
    compliant
    0.06
     لأنه
    0.06
    Activations Density 0.001%

    No Known Activations