© 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. 115961
    Prev
    Next
    INDEX
    Explanations

    all areas or workers

    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
     smaller
    -0.06
     propia
    -0.06
     LIABLE
    -0.06
     apni
    -0.06
    史上
    -0.06
     якщо
    -0.05
     pouze
    -0.05
     sotto
    -0.05
     अगर
    -0.05
     eval
    -0.05
    POSITIVE LOGITS
     freeing
    0.07
    ઙ
    0.06
    mtrl
    0.06
     ב
    0.05
     unearthed
    0.05
     withstood
    0.05
     الاجتما
    0.05
    堅持
    0.05
     filtr
    0.05
     maneuvers
    0.05
    Activations Density 0.001%

    No Known Activations