© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119008
    Prev
    Next
    INDEX
    Explanations

    century battle

    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
     früheren
    -0.06
     langsung
    -0.06
     بالج
    -0.06
     brauchen
    -0.06
    𝙠
    -0.06
     современ
    -0.06
    Last
    -0.06
    immediately
    -0.06
     letz
    -0.06
    Immediate
    -0.06
    POSITIVE LOGITS
     afin
    0.07
     infancy
    0.07
    เพื่อให้
    0.06
    rather
    0.06
     αφ
    0.06
     Rather
    0.06
     rather
    0.06
     정보를
    0.06
    Rather
    0.06
     ಇನ್ನೂ
    0.06
    Activations Density 0.002%

    No Known Activations