© 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. 127916
    Prev
    Next
    INDEX
    Explanations

    months and days

    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
     এবার
    -0.07
    Según
    -0.06
    According
    -0.06
     volver
    -0.06
     जांच
    -0.06
     könnte
    -0.06
     ممکن
    -0.06
     concerts
    -0.06
     month
    -0.06
     mùa
    -0.06
    POSITIVE LOGITS
     by
    0.08
     preferably
    0.07
     facilitate
    0.07
     любых
    0.06
    by
    0.06
    preferably
    0.06
     তারা
    0.06
     when
    0.06
     når
    0.06
     NTIS
    0.06
    Activations Density 0.024%

    No Known Activations