© 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. 127912
    Prev
    Next
    INDEX
    Explanations

    date or starting point

    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
    urdy
    -0.06
     definido
    -0.06
     når
    -0.06
     detour
    -0.06
     অভ্যন্তরীণ
    -0.06
     after
    -0.06
     justify
    -0.05
     disregarding
    -0.05
     中
    -0.05
     després
    -0.05
    POSITIVE LOGITS
     їх
    0.06
     அவற்றில்
    0.06
     их
    0.06
     события
    0.06
     événement
    0.06
     nuov
    0.06
     발생
    0.06
     사건
    0.06
     commencement
    0.06
     सक्रिय
    0.06
    Activations Density 0.005%

    No Known Activations