© 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. 128524
    Prev
    Next
    INDEX
    Explanations

    can

    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
     multitask
    -0.06
     على
    -0.06
     ك
    -0.06
    izaciones
    -0.06
     lớn
    -0.06
     Corresponding
    -0.06
    ظيم
    -0.05
    correspond
    -0.05
     согласно
    -0.05
     अधिका
    -0.05
    POSITIVE LOGITS
     benchmarking
    0.06
     exporting
    0.06
     vég
    0.06
    📊
    0.06
    receive
    0.06
    🏷
    0.06
    🥫
    0.06
     fehlen
    0.06
     Export
    0.06
     trenut
    0.06
    Activations Density 0.015%

    No Known Activations