© 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. 119743
    Prev
    Next
    INDEX
    Explanations

    known practice or meaning

    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
     高
    -0.08
     what
    -0.07
     三
    -0.07
     大
    -0.06
     ク
    -0.06
     外
    -0.06
     helps
    -0.06
     バ
    -0.06
    What
    -0.06
     リ
    -0.06
    POSITIVE LOGITS
    だった
    0.07
    했는데
    0.07
    全新的
    0.06
    新しい
    0.06
    🥺
    0.06
     erforder
    0.06
    新的
    0.06
     주로
    0.06
     soltanto
    0.06
     tanto
    0.06
    Activations Density 0.057%

    No Known Activations