© 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. 130270
    Prev
    Next
    INDEX
    Explanations

    assert(...)

    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
     Gesamt
    -0.06
    ）、
    -0.06
    を有する
    -0.06
     outfitted
    -0.06
    ６
    -0.06
     aggravated
    -0.06
     faraway
    -0.06
     falsch
    -0.05
    রেক
    -0.05
    cdot
    -0.05
    POSITIVE LOGITS
     максимально
    0.07
     что
    0.07
     обычно
    0.06
     geralmente
    0.06
     по
    0.06
     biasanya
    0.06
     не
    0.06
    omerang
    0.06
    Typically
    0.06
     typically
    0.06
    Activations Density 0.001%

    No Known Activations