© 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. 121057
    Prev
    Next
    INDEX
    Explanations

    quantities

    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
    iei
    -0.06
     כול
    -0.06
     எல்லா
    -0.06
    ča
    -0.06
     with
    -0.06
    BS
    -0.06
    ios
    -0.05
    еве
    -0.05
     over
    -0.05
     খুবই
    -0.05
    POSITIVE LOGITS
     purposely
    0.07
     LIVING
    0.07
     intentionally
    0.07
    Living
    0.06
    如果你
    0.06
     purposefully
    0.06
     logically
    0.06
    كَ
    0.06
    Captain
    0.06
    如果
    0.06
    Activations Density 0.019%

    No Known Activations