© 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. 120745
    Prev
    Next
    INDEX
    Explanations

    GNU Lesser General Public License

    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
    Not in Any Lists

    No Comments

    Negative Logits
    新的
    -0.08
     prachtige
    -0.07
     új
    -0.06
     berikut
    -0.06
     kini
    -0.06
     creciente
    -0.06
     новой
    -0.06
     kota
    -0.06
    から
    -0.06
     नए
    -0.06
    POSITIVE LOGITS
    ionu
    0.07
     برای
    0.07
     人
    0.07
    rmann
    0.07
     外
    0.06
     casually
    0.06
    မှုကို
    0.06
     unsurprisingly
    0.06
     noticeably
    0.06
     volunte
    0.06
    Activations Density 0.008%

    No Known Activations