© 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. 129584
    Prev
    Next
    INDEX
    Explanations

    code and programming examples

    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
     استفاده
    -0.06
     oft
    -0.06
    ări
    -0.06
     occurrences
    -0.06
     activiteiten
    -0.06
     utilização
    -0.06
     použití
    -0.05
     since
    -0.05
     kegiatan
    -0.05
     activates
    -0.05
    POSITIVE LOGITS
     tanpa
    0.06
     can
    0.06
    这里的
    0.06
     pixel
    0.06
    也可以
    0.06
     Carpent
    0.06
     kõr
    0.06
    还可以
    0.06
     этих
    0.06
     Terc
    0.06
    Activations Density 0.001%

    No Known Activations