© 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. 119950
    Prev
    Next
    INDEX
    Explanations

    probability of sequences

    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
    Эти
    -0.07
     these
    -0.07
     non
    -0.06
     tych
    -0.06
     EQS
    -0.06
     essas
    -0.06
     ঘরে
    -0.06
     ovih
    -0.06
     casi
    -0.06
    間違い
    -0.06
    POSITIVE LOGITS
     পারছেন
    0.06
     calle
    0.06
     psychic
    0.06
    鼗
    0.06
    immen
    0.06
    dub
    0.05
    ည့်
    0.05
     मौर्य
    0.05
    ೂರ
    0.05
     さらに
    0.05
    Activations Density 0.001%

    No Known Activations