© 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. 119087
    Prev
    Next
    INDEX
    Explanations

    slowing down

    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
     plastique
    -0.07
     максима
    -0.06
    कृष्ट
    -0.06
     детский
    -0.06
     humana
    -0.06
     Zoology
    -0.06
     건축
    -0.06
     Japon
    -0.06
     użytk
    -0.06
     maximum
    -0.06
    POSITIVE LOGITS
     lights
    0.07
     isso
    0.06
     piracy
    0.06
     starboard
    0.06
     Lights
    0.06
     lifeboat
    0.06
     attività
    0.06
     impoverished
    0.06
     serious
    0.06
     listing
    0.06
    Activations Density 0.012%

    No Known Activations