© 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. 129327
    Prev
    Next
    INDEX
    Explanations

    specifications and descriptors

    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
     which
    -0.06
     ಅನ್ನ
    -0.06
     questo
    -0.06
    これも
    -0.06
    つく
    -0.06
     diesem
    -0.06
     ತೆಗೆದುಕೊಳ್ಳ
    -0.06
    ;
    -0.05
    ènement
    -0.05
    亞
    -0.05
    POSITIVE LOGITS
     descriptor
    0.07
     stating
    0.06
     Fine
    0.06
    再次
    0.06
    ounter
    0.06
     clarity
    0.06
     cajas
    0.06
    的目的
    0.06
     proyectos
    0.06
     descriptors
    0.06
    Activations Density 0.004%

    No Known Activations