© 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. 128169
    Prev
    Next
    INDEX
    Explanations

    Ant, Cam, Q sequences

    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
     иногда
    -0.08
     অথবা
    -0.07
     sürekli
    -0.07
     arī
    -0.06
     либо
    -0.06
    レイン
    -0.06
     ಹೃದಯ
    -0.06
    玑
    -0.06
     항상
    -0.06
     বলেও
    -0.06
    POSITIVE LOGITS
     where
    0.06
    ,
    0.06
    *,
    0.06
    WHERE
    0.06
    Where
    0.06
    新
    0.06
     在
    0.05
    тив
    0.05
    上述
    0.05
    automatic
    0.05
    Activations Density 0.005%

    No Known Activations