© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116299
    Prev
    Next
    INDEX
    Explanations

    study done

    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
     bolster
    -0.06
     reprezent
    -0.06
     barring
    -0.06
     REPRESENT
    -0.06
     služby
    -0.06
     sayfası
    -0.06
     descoper
    -0.06
    早速
    -0.06
     bulunan
    -0.06
    gister
    -0.06
    POSITIVE LOGITS
     entw
    0.06
     intertwined
    0.06
     নির্বাচনী
    0.06
     зовніш
    0.06
     надо
    0.06
    ও
    0.06
     braided
    0.06
     doğum
    0.06
    𝐡
    0.06
     mixture
    0.05
    Activations Density 0.004%

    No Known Activations