© 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. 119796
    Prev
    Next
    INDEX
    Explanations

    research proposal construction

    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
     gesamten
    -0.06
     activités
    -0.05
     disini
    -0.05
    MED
    -0.05
     Activity
    -0.05
     функциона
    -0.05
    ieves
    -0.05
    穿
    -0.05
     here
    -0.05
    View
    -0.05
    POSITIVE LOGITS
     stipulations
    0.07
    Construction
    0.06
     myriad
    0.06
    construction
    0.06
     dormitorios
    0.06
     auster
    0.06
     chúng
    0.06
     Construction
    0.06
    ClientId
    0.06
     construction
    0.06
    Activations Density 0.005%

    No Known Activations