© 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. 118931
    Prev
    Next
    INDEX
    Explanations

    XML functions like contains

    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
     tylko
    -0.08
     Sudah
    -0.07
     with
    -0.07
     уже
    -0.07
     daž
    -0.07
     только
    -0.07
     slechts
    -0.06
    이미
    -0.06
     pouze
    -0.06
    すでに
    -0.06
    POSITIVE LOGITS
     গ্রাম
    0.07
     сё
    0.06
    
    0.06
    systems
    0.06
     වැඩ
    0.06
     Campania
    0.06
    urgia
    0.05
     couv
    0.05
     creating
    0.05
     avancé
    0.05
    Activations Density 0.001%

    No Known Activations