© 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. 128233
    Prev
    Next
    INDEX
    Explanations

    places and historical sites

    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
    țional
    -0.06
     useful
    -0.06
     ​​
    -0.06
     coast
    -0.06
     beaches
    -0.06
    单词
    -0.06
     ice
    -0.06
     कोक
    -0.06
    τρι
    -0.06
    shore
    -0.06
    POSITIVE LOGITS
     specify
    0.07
     absolue
    0.06
     HEALTH
    0.06
     superbly
    0.06
     sağlık
    0.06
    massive
    0.06
    慢性
    0.06
     বিশাল
    0.06
    ofu
    0.06
    困難
    0.06
    Activations Density 0.007%

    No Known Activations