© 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. 118575
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
     dunque
    -0.08
     therefore
    -0.08
     quindi
    -0.08
     portanto
    -0.07
     그러나
    -0.07
    그러나
    -0.06
     как
    -0.06
     alcuni
    -0.06
     Consequently
    -0.06
    西兰
    -0.06
    POSITIVE LOGITS
     타고
    0.06
     ever
    0.06
     高
    0.06
    ेडकर
    0.06
     इसको
    0.06
     debilitating
    0.06
     irreplaceable
    0.05
     already
    0.05
    ℅
    0.05
    ابي
    0.05
    Activations Density 0.018%

    No Known Activations