© 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. 118113
    Prev
    Next
    INDEX
    Explanations

    symbol definitions

    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
     bạn
    -0.07
    ቒ
    -0.06
     afar
    -0.06
    atibus
    -0.06
    万円
    -0.06
     overpowered
    -0.06
    orkeling
    -0.06
    处
    -0.06
     transporte
    -0.06
    bromo
    -0.06
    POSITIVE LOGITS
     followed
    0.06
     باعث
    0.06
    改
    0.06
    井
    0.06
     precise
    0.05
     voluptas
    0.05
     、
    0.05
     imprecise
    0.05
    dolo
    0.05
     //
    0.05
    Activations Density 0.001%

    No Known Activations