© 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. 117633
    Prev
    Next
    INDEX
    Explanations

    show that

    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
     required
    -0.07
     necesario
    -0.07
     (?)
    -0.06
     after
    -0.06
    !:
    -0.06
     (?
    -0.06
    !!
    -0.06
     incandescent
    -0.06
     hip
    -0.06
    すること
    -0.06
    POSITIVE LOGITS
     및
    0.06
    CL
    0.06
     लॉग
    0.06
     একইভাবে
    0.06
     suele
    0.06
     samego
    0.06
     религи
    0.06
     suelen
    0.06
     zonder
    0.06
     religiosos
    0.06
    Activations Density 0.002%

    No Known Activations