© 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. 116962
    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
     acaba
    -0.06
     moje
    -0.06
     When
    -0.06
     adaptador
    -0.06
     folgenden
    -0.06
     نیشنل
    -0.06
     utilizar
    -0.06
     eine
    -0.06
    难道
    -0.06
     mno
    -0.06
    POSITIVE LOGITS
    與
    0.07
    nd
    0.06
    di
    0.06
     दोनों
    0.06
     मानते
    0.06
    ोटी
    0.06
    与
    0.06
     hacen
    0.06
    "—
    0.06
    its
    0.05
    Activations Density 0.000%

    No Known Activations