© 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. 129232
    Prev
    Next
    INDEX
    Explanations

    php bundled

    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
     тогда
    -0.07
    综合
    -0.06
    取出
    -0.06
     संयंत्र
    -0.06
     také
    -0.06
    worst
    -0.06
     hoặc
    -0.06
    綜合
    -0.06
     perfected
    -0.06
    bringing
    -0.06
    POSITIVE LOGITS
     각종
    0.07
    っているので
    0.06
    他不
    0.06
    これからも
    0.06
    始めた
    0.06
     sür
    0.05
     основных
    0.05
     MAINT
    0.05
     Scholarship
    0.05
     deten
    0.05
    Activations Density 0.005%

    No Known Activations