© 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. 119914
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     noget
    -0.06
     annum
    -0.06
     under
    -0.06
     aflat
    -0.06
     refracted
    -0.06
     prossimo
    -0.06
     centred
    -0.05
     ডাক্তারের
    -0.05
     bilo
    -0.05
     jaun
    -0.05
    POSITIVE LOGITS
     управлять
    0.06
    aktor
    0.06
     সিদ্ধান্ত
    0.06
    ❖
    0.06
     لگتا
    0.06
     অধ্যাপক
    0.05
     شناخت
    0.05
     appropriate
    0.05
     ಹೆ
    0.05
     मेंबर
    0.05
    Activations Density 0.000%

    No Known Activations