© 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. 116058
    Prev
    Next
    INDEX
    Explanations

    connecting with others

    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
     you
    -0.08
    You
    -0.08
     You
    -0.07
     ),
    -0.06
    you
    -0.06
    …
    -0.06
    Our
    -0.06
     ну
    -0.06
     attuned
    -0.06
     pertinent
    -0.06
    POSITIVE LOGITS
     dengan
    0.09
     by
    0.09
     with
    0.08
     với
    0.08
     algunas
    0.07
    いくつかの
    0.07
     algunos
    0.07
     కొన్ని
    0.07
     namely
    0.07
     עם
    0.07
    Activations Density 0.028%

    No Known Activations