© 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. 116997
    Prev
    Next
    INDEX
    Explanations

    types of cases

    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
    Lastly
    -0.07
     পাচ
    -0.06
     such
    -0.06
     justamente
    -0.06
    either
    -0.06
    ่วย
    -0.06
    coupled
    -0.06
     coupled
    -0.06
    このような
    -0.06
     firstly
    -0.06
    POSITIVE LOGITS
     apprentice
    0.06
     Get
    0.06
    ക്കോ
    0.06
    갬
    0.06
     경우가
    0.06
    ideos
    0.06
    الم
    0.06
    说说
    0.06
     spesso
    0.06
     경우
    0.06
    Activations Density 0.011%

    No Known Activations