© 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. 128906
    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
     रिया
    -0.07
     of
    -0.06
     trouve
    -0.06
    ilon
    -0.05
     reduction
    -0.05
     que
    -0.05
     TIME
    -0.05
     নেতৃত্বের
    -0.05
     achieve
    -0.05
    क्रोश
    -0.05
    POSITIVE LOGITS
    ้อมูล
    0.08
    ข้อมูล
    0.07
     پیسے
    0.06
    лександр
    0.06
    owań
    0.06
     जोड
    0.06
    μένου
    0.06
     сведения
    0.06
    ודי
    0.06
    哟
    0.06
    Activations Density 0.000%

    No Known Activations