© 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. 120813
    Prev
    Next
    INDEX
    Explanations

    or/and

    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
     other
    -0.09
    其他
    -0.08
    他の
    -0.08
    其它
    -0.08
     остальные
    -0.07
     अन्य
    -0.07
     diğer
    -0.07
    其余
    -0.07
    その他
    -0.07
     बाकी
    -0.07
    POSITIVE LOGITS
     bzw
    0.06
    traumatic
    0.06
     específicos
    0.06
     Zusammenhang
    0.06
    specific
    0.06
    contest
    0.06
     basa
    0.06
     tomo
    0.05
     specifically
    0.05
     alter
    0.05
    Activations Density 0.041%

    No Known Activations