© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118155
    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
     be
    -0.07
    -',
    -0.06
    ogle
    -0.06
    telefon
    -0.06
     significant
    -0.06
     !!
    -0.06
     !!!
    -0.06
    глежда
    -0.06
    ────
    -0.06
    screenshots
    -0.06
    POSITIVE LOGITS
    下次
    0.06
     एवं
    0.06
    かつ
    0.06
     সহায়
    0.06
     ं
    0.06
    倜
    0.06
     späteren
    0.06
     whose
    0.05
     πραγμα
    0.05
     cuyas
    0.05
    Activations Density 0.000%

    No Known Activations