© 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. 130214
    Prev
    Next
    INDEX
    Explanations

    legal action, invoke, summoned, measures

    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
     otros
    -0.08
    鸭
    -0.07
    その他
    -0.07
     дальней
    -0.07
    urther
    -0.07
     belirl
    -0.07
     determinados
    -0.07
     autres
    -0.07
     diğer
    -0.07
     अन्य
    -0.06
    POSITIVE LOGITS
     has
    0.07
     now
    0.06
     développ
    0.06
     Dodson
    0.06
     Fr
    0.06
     misused
    0.06
    vm
    0.05
     लो
    0.05
     counselor
    0.05
     forhold
    0.05
    Activations Density 0.017%

    No Known Activations