© 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. 129272
    Prev
    Next
    INDEX
    Explanations

    HTML5

    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
    ısının
    -0.06
     свое
    -0.06
     ديال
    -0.06
     unrecognizable
    -0.06
    changed
    -0.06
     racional
    -0.06
     cambió
    -0.06
     умолча
    -0.05
     فیصلے
    -0.05
     uniform
    -0.05
    POSITIVE LOGITS
    振
    0.06
     não
    0.06
    范围内
    0.06
     그는
    0.06
     permissible
    0.06
     feasible
    0.06
     അദ്ദേഹം
    0.06
    aol
    0.06
    titles
    0.06
     знаю
    0.06
    Activations Density 0.003%

    No Known Activations