© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128041
    Prev
    Next
    INDEX
    Explanations

    relative percentage ratio

    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
    Negative Logits
    之间
    -0.06
    GAIN
    -0.06
    MF
    -0.05
    都合
    -0.05
     proper
    -0.05
     gain
    -0.05
     EVENTS
    -0.05
     greater
    -0.05
    において
    -0.05
     bale
    -0.05
    POSITIVE LOGITS
     permitt
    0.07
     permettre
    0.07
     permit
    0.07
     isang
    0.07
    了两
    0.06
     controvers
    0.06
    റോ
    0.06
     разрабо
    0.06
     tahu
    0.06
     eruption
    0.06
    Activations Density 0.015%

    No Known Activations