© 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. 115966
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
    独特的
    -0.07
     instrument
    -0.06
     its
    -0.06
     obligatory
    -0.06
    CTAssert
    -0.06
    Secrets
    -0.06
    撥
    -0.06
    最好
    -0.06
     обязательно
    -0.06
    programs
    -0.06
    POSITIVE LOGITS
     주기
    0.07
     currently
    0.07
    Currently
    0.07
     solchen
    0.06
     hoping
    0.06
     jaar
    0.06
    なぁ
    0.06
     હાલ
    0.06
     Currently
    0.06
    今後
    0.06
    Activations Density 0.005%

    No Known Activations