© 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. 120460
    Prev
    Next
    INDEX
    Explanations

    css unit measurements

    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
     agak
    -0.06
     However
    -0.06
     Б
    -0.06
     Exceptions
    -0.06
     Wurzel
    -0.06
     getting
    -0.06
     somewhat
    -0.05
    Exceptions
    -0.05
     বৌ
    -0.05
     বিরোধিতা
    -0.05
    POSITIVE LOGITS
    最后
    0.08
    立刻
    0.06
    僄
    0.06
    뿐
    0.06
    也将
    0.06
    あと
    0.06
    每一
    0.06
    部长
    0.06
    ValArr
    0.06
    will
    0.06
    Activations Density 0.001%

    No Known Activations