© 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. 119941
    Prev
    Next
    INDEX
    Explanations

    keys followed by colon or quote

    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
    ²,
    -0.07
    idades
    -0.06
    ,
    -0.06
    And
    -0.06
    *,
    -0.06
    店铺
    -0.06
    init
    -0.06
    珺
    -0.06
     строку
    -0.06
     designed
    -0.06
    POSITIVE LOGITS
    arning
    0.06
    pictureBox
    0.06
     February
    0.06
     occasione
    0.06
     maxY
    0.06
    getMax
    0.06
    රි
    0.06
     맞아
    0.06
     MaxPooling
    0.05
     最大
    0.05
    Activations Density 0.001%

    No Known Activations