© 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. 116935
    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
     mysteriously
    -0.07
     horribly
    -0.06
    contest
    -0.06
     moj
    -0.06
     softly
    -0.06
    ರಿಗೆ
    -0.06
     gently
    -0.06
     cones
    -0.06
    চনার
    -0.06
    觟
    -0.06
    POSITIVE LOGITS
    anym
    0.07
     대표
    0.06
     prea
    0.06
    ใน
    0.06
    ждать
    0.06
     pertinent
    0.06
     such
    0.06
     immunore
    0.06
     comprehensive
    0.06
     നിന്നും
    0.06
    Activations Density 0.000%

    No Known Activations