© 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. 116455
    Prev
    Next
    INDEX
    Explanations

    html tags and attributes

    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
    兒子
    -0.07
    我們
    -0.07
     nasz
    -0.07
    ပါ
    -0.06
    र्जर
    -0.06
    小于
    -0.06
     reconciled
    -0.06
    在国内
    -0.06
    szyst
    -0.06
     comenzamos
    -0.06
    POSITIVE LOGITS
     ওদের
    0.06
    或
    0.06
    いくつかの
    0.06
    4
    0.06
    様々な
    0.06
    JS
    0.05
    US
    0.05
    Finn
    0.05
     some
    0.05
    mann
    0.05
    Activations Density 0.002%

    No Known Activations