© 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. 119861
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
     aren
    -0.07
     underpinned
    -0.06
     revamp
    -0.06
     incorporating
    -0.06
     whatnot
    -0.06
     Leisure
    -0.06
     pursuits
    -0.06
     devising
    -0.06
     nggak
    -0.06
     sondern
    -0.06
    POSITIVE LOGITS
     дуже
    0.07
     очень
    0.07
     This
    0.07
     ఒక
    0.07
     very
    0.06
     هذا
    0.06
     While
    0.06
     careful
    0.06
     this
    0.06
     sehr
    0.06
    Activations Density 0.038%

    No Known Activations