© 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. 129097
    Prev
    Next
    INDEX
    Explanations

    with positive outcomes

    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
     provides
    -0.07
     supremely
    -0.07
     intertwined
    -0.07
     masterful
    -0.07
     allows
    -0.06
    들과
    -0.06
     creates
    -0.06
     powerfully
    -0.06
     ഒരാ
    -0.06
     abiding
    -0.06
    POSITIVE LOGITS
     that
    0.06
    western
    0.06
     qualquer
    0.06
     घेण्यात
    0.06
     lebih
    0.06
    Western
    0.06
    未
    0.06
    分为
    0.05
    9
    0.05
     كه
    0.05
    Activations Density 0.073%

    No Known Activations