© 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. 115989
    Prev
    Next
    INDEX
    Explanations

    full, complete, entire, whole

    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
     świet
    -0.06
     तपाई
    -0.06
     type
    -0.06
     another
    -0.06
    type
    -0.06
    DOCKED
    -0.06
     whence
    -0.06
     Further
    -0.06
     further
    -0.05
     Hepat
    -0.05
    POSITIVE LOGITS
     possesses
    0.07
    正確
    0.07
     শুধুমাত্র
    0.06
     Frederik
    0.06
     is
    0.06
     بال
    0.06
     بشكل
    0.06
     Secara
    0.06
     Maks
    0.06
     circumstantial
    0.06
    Activations Density 0.012%

    No Known Activations