© 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. 130581
    Prev
    Next
    INDEX
    Explanations

    First name / Surname

    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
     reaffirmed
    -0.07
     Usually
    -0.07
    responsive
    -0.06
     хороший
    -0.06
     reaffirm
    -0.06
    unless
    -0.06
     ግን
    -0.06
     Обычно
    -0.06
     validated
    -0.06
     rivulet
    -0.06
    POSITIVE LOGITS
     egyes
    0.06
    μένων
    0.06
    where
    0.06
    Wie
    0.05
    toto
    0.05
    捛
    0.05
     debemos
    0.05
    ㊙
    0.05
     Nez
    0.05
     eighteenth
    0.05
    Activations Density 0.010%

    No Known Activations