© 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. 120074
    Prev
    Next
    INDEX
    Explanations

    text following ordinal or year

    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
    悝
    -0.06
    ಹು
    -0.06
     Solutions
    -0.06
    评论
    -0.06
     system
    -0.06
     som
    -0.06
     като
    -0.06
    oes
    -0.06
    ಾರು
    -0.06
     SOLUTIONS
    -0.06
    POSITIVE LOGITS
     about
    0.06
     തീരുമാന
    0.06
     энерго
    0.05
     décrite
    0.05
     denna
    0.05
     মসজিদ
    0.05
     dip
    0.05
    ２
    0.05
    lllll
    0.05
    aceted
    0.05
    Activations Density 0.049%

    No Known Activations