© 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. 128562
    Prev
    Next
    INDEX
    Explanations

    unactivated, naive, untreated, closed, normal, null

    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
     новая
    -0.07
     새로
    -0.07
    初めて
    -0.06
     کرده
    -0.06
     புதிய
    -0.06
     newcomers
    -0.06
     miesią
    -0.06
     новые
    -0.06
    solid
    -0.06
     new
    -0.06
    POSITIVE LOGITS
     untouched
    0.08
     unaltered
    0.07
    を選ぶ
    0.06
     undisturbed
    0.06
     unchanged
    0.06
     घेण्यात
    0.06
     фильме
    0.06
     unsupervised
    0.06
    ঞ্চল
    0.06
     unchecked
    0.06
    Activations Density 0.038%

    No Known Activations