© 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. 129130
    Prev
    Next
    INDEX
    Explanations

    vs / against

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    張り
    -0.07
    લે
    -0.06
     unattractive
    -0.06
    起始
    -0.06
     faraway
    -0.06
     впер
    -0.06
     Medications
    -0.06
     THEIR
    -0.06
     처음
    -0.06
     impenetrable
    -0.06
    POSITIVE LOGITS
     privately
    0.08
     community
    0.07
     used
    0.06
     ஈடுபட்ட
    0.06
     około
    0.06
     commercially
    0.06
    community
    0.06
     experimentally
    0.06
    ใช้
    0.06
     monumento
    0.06
    Activations Density 0.011%

    No Known Activations