© 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. 128214
    Prev
    Next
    INDEX
    Explanations

    other words or characters

    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
     үш
    -0.07
     Odessa
    -0.07
     Corfu
    -0.07
    んだろう
    -0.06
     lapses
    -0.06
    のひとつ
    -0.06
     четырех
    -0.06
     Femme
    -0.06
    恢复
    -0.06
    olon
    -0.06
    POSITIVE LOGITS
     ஆதர
    0.07
    その他
    0.06
    etc
    0.06
     else
    0.06
     دیگر
    0.05
     kedua
    0.05
    ほか
    0.05
     otherwise
    0.05
    ities
    0.05
     other
    0.05
    Activations Density 0.011%

    No Known Activations