© 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. 119240
    Prev
    Next
    INDEX
    Explanations

    trademark registered

    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
    uegos
    -0.06
    または
    -0.06
    酩
    -0.06
    חר
    -0.06
     wollen
    -0.06
    व्यक्ति
    -0.06
     журнала
    -0.06
    ISK
    -0.06
    決定
    -0.06
     危
    -0.06
    POSITIVE LOGITS
     बेशक
    0.06
    ;
    0.06
     propias
    0.06
     
    0.06
    Its
    0.06
     Its
    0.06
    http
    0.06
    its
    0.06
     tecnologias
    0.06
    find
    0.05
    Activations Density 0.001%

    No Known Activations