© 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. 119508
    Prev
    Next
    INDEX
    Explanations

    web request urlopen urlopen urlopen

    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
    বিভিন্ন
    -0.07
     istiyorum
    -0.06
     voulez
    -0.06
     інші
    -0.06
     ಹೆಚ್ಚು
    -0.06
    ニア
    -0.06
     élevé
    -0.06
     ಇನ್ನೂ
    -0.06
    트
    -0.06
    SHALL
    -0.06
    POSITIVE LOGITS
     messes
    0.07
     duen
    0.07
    abet
    0.06
     รวมถึง
    0.06
    engkap
    0.06
     Chaplain
    0.06
     contours
    0.06
    COLORS
    0.06
    }\|^{
    0.06
     Incorpor
    0.06
    Activations Density 0.004%

    No Known Activations