© 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. 121012
    Prev
    Next
    INDEX
    Explanations

    parameter assignment or variable declaration

    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
     XI
    -0.07
     .\
    -0.06
     that
    -0.06
    ॉग
    -0.06
    💯
    -0.05
     dos
    -0.05
    akta
    -0.05
    osite
    -0.05
    湇
    -0.05
    чный
    -0.05
    POSITIVE LOGITS
     strange
    0.07
     startled
    0.07
     Vielen
    0.06
     تقریباً
    0.06
    tidak
    0.06
     jihad
    0.06
     अभिनंदन
    0.06
    แปล
    0.06
     may
    0.06
     стран
    0.06
    Activations Density 0.002%

    No Known Activations