© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117959
    Prev
    Next
    INDEX
    Explanations

    listing or separation

    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
     δεν
    -0.08
     없
    -0.07
     não
    -0.07
    虽然
    -0.07
     olmadan
    -0.07
    없
    -0.07
     ٹی
    -0.07
    នៅ
    -0.07
     buget
    -0.06
    Lantern
    -0.06
    POSITIVE LOGITS
     a
    0.06
     luscious
    0.06
     or
    0.06
     world
    0.06
     හෝ
    0.06
     bzw
    0.06
     engulfed
    0.05
     lös
    0.05
     নিষ্
    0.05
     নীর
    0.05
    Activations Density 0.019%

    No Known Activations