© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128837
    Prev
    Next
    INDEX
    Explanations

    focus and distraction

    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
     rehearsal
    -0.06
     religión
    -0.06
     daylight
    -0.06
     влияние
    -0.06
     влияния
    -0.06
     dėl
    -0.06
     উচ্চ
    -0.06
    Scheduling
    -0.06
     प्रसार
    -0.06
     wpływ
    -0.06
    POSITIVE LOGITS
     distracted
    0.09
     distract
    0.06
     большинстве
    0.06
    вают
    0.06
     majority
    0.06
    тивными
    0.06
     omoguć
    0.06
     latéral
    0.06
     distraction
    0.06
     తొలి
    0.05
    Activations Density 0.012%

    No Known Activations