© 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. 128834
    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
     wyłącznie
    -0.07
     ainult
    -0.06
     cens
    -0.06
    是因為
    -0.06
    家长
    -0.06
     fein
    -0.06
     échantillons
    -0.06
     przedsiębior
    -0.06
     ihres
    -0.06
     altri
    -0.06
    POSITIVE LOGITS
     pertinent
    0.07
     tiene
    0.06
     doesn
    0.06
     nighttime
    0.06
     makes
    0.06
    曾在
    0.06
     pertinente
    0.06
     voire
    0.06
    \`
    0.06
     جدید
    0.06
    Activations Density 0.000%

    No Known Activations