© 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. 130434
    Prev
    Next
    INDEX
    Explanations

    depending on conditions

    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
     one
    -0.07
     an
    -0.07
    是由
    -0.06
     unter
    -0.06
     onder
    -0.06
     allemaal
    -0.06
    জাতির
    -0.06
     una
    -0.06
    一個
    -0.06
     mattis
    -0.06
    POSITIVE LOGITS
     इनको
    0.08
     pourraient
    0.06
     savent
    0.06
     мають
    0.06
     COULD
    0.06
    гі
    0.06
     것으로
    0.06
     consequently
    0.06
     designate
    0.05
     corroborated
    0.05
    Activations Density 0.007%

    No Known Activations