© 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. 119505
    Prev
    Next
    INDEX
    Explanations

    Late complications, differential staining

    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
     당신
    -0.07
    謊
    -0.06
     Cuando
    -0.06
     संदिग्ध
    -0.06
     Когда
    -0.06
     большей
    -0.06
     рядом
    -0.06
    OWL
    -0.06
     prodotto
    -0.06
     मनोरंजन
    -0.06
    POSITIVE LOGITS
     ''
    0.06
    看来
    0.06
    winter
    0.06
    겪
    0.05
    period
    0.05
    काळी
    0.05
     fuh
    0.05
     experiencing
    0.05
     wife
    0.05
     winter
    0.05
    Activations Density 0.006%

    No Known Activations