© 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. 128234
    Prev
    Next
    INDEX
    Explanations

    list item identifiers or structure

    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
    她
    -0.07
     आम्ही
    -0.07
     シ
    -0.06
     एसटी
    -0.06
     की
    -0.06
     sobretudo
    -0.06
     her
    -0.06
     infographic
    -0.06
    完全
    -0.06
    ährung
    -0.06
    POSITIVE LOGITS
     বিমানের
    0.06
     "
    0.06
    Where
    0.06
     "...
    0.06
     outpost
    0.06
    counter
    0.06
     बकाया
    0.05
    пропетров
    0.05
     halen
    0.05
     ;(
    0.05
    Activations Density 0.001%

    No Known Activations