© 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. 117064
    Prev
    Next
    INDEX
    Explanations

    change or changes

    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
     beper
    -0.07
     limitaciones
    -0.07
     محدود
    -0.07
     ograni
    -0.07
     limitations
    -0.06
    ambarkan
    -0.06
     обме
    -0.06
    限制
    -0.06
    制限
    -0.06
     restricts
    -0.06
    POSITIVE LOGITS
     changes
    0.08
     changements
    0.08
     change
    0.07
    changes
    0.07
     Change
    0.07
     تغيير
    0.07
     değişiklik
    0.07
     changé
    0.07
     perubahan
    0.07
     mudança
    0.07
    Activations Density 0.002%

    No Known Activations