© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131006
    Prev
    Next
    INDEX
    Explanations

    following region

    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
     よく
    -0.07
    非常に
    -0.07
    㖘
    -0.07
     strangely
    -0.07
    よく
    -0.07
     vividly
    -0.07
     seriously
    -0.06
     happily
    -0.06
     decidedly
    -0.06
     labai
    -0.06
    POSITIVE LOGITS
     -
    0.07
     geführt
    0.06
     INPUT
    0.06
    :
    0.06
    ्यास
    0.05
     input
    0.05
    其他的
    0.05
     önces
    0.05
     keempat
    0.05
     Eltern
    0.05
    Activations Density 0.008%

    No Known Activations