© 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. 117372
    Prev
    Next
    INDEX
    Explanations

    Include, url, and prepositional phrases like "to"

    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
    لاص
    -0.06
     पुलिस
    -0.06
    chetto
    -0.05
    ッシ
    -0.05
    皮肤
    -0.05
    大好き
    -0.05
    期望
    -0.05
    กับ
    -0.05
     বাঙ্গ
    -0.05
     বাঙ্গালী
    -0.05
    POSITIVE LOGITS
     एवं
    0.06
     and
    0.06
     वैदिक
    0.06
     والنصف
    0.06
     contributed
    0.06
     إذا
    0.06
     philosopher
    0.06
    以及
    0.06
     क्रांतिक
    0.05
     nonché
    0.05
    Activations Density 0.001%

    No Known Activations