© 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. 116334
    Prev
    Next
    INDEX
    Explanations

    type additional

    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
    环保
    -0.07
     của
    -0.07
    currentPlayer
    -0.07
    繰り返し
    -0.07
     シンプル
    -0.07
    របស់យើង
    -0.06
     У
    -0.06
    സ
    -0.06
     whichever
    -0.06
     Մ
    -0.06
    POSITIVE LOGITS
    additional
    0.07
     weitere
    0.07
    :
    0.07
     additional
    0.07
    Type
    0.06
    Additional
    0.06
     கூடுதல்
    0.06
     accompanying
    0.06
    type
    0.06
    transformed
    0.05
    Activations Density 0.006%

    No Known Activations