© 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. 120455
    Prev
    Next
    INDEX
    Explanations

    searching for `available` or `sources`

    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
    當然
    -0.07
     ederim
    -0.07
     tijdens
    -0.07
    ör
    -0.07
     during
    -0.07
     während
    -0.07
    当然
    -0.06
     isn
    -0.06
    ുകയും
    -0.06
     ตอน
    -0.06
    POSITIVE LOGITS
    SOURCES
    0.06
     ग्रोथ
    0.06
    source
    0.06
    sources
    0.06
     источ
    0.05
     Doing
    0.05
     Alone
    0.05
    SOURCE
    0.05
     source
    0.05
     Africa
    0.05
    Activations Density 0.001%

    No Known Activations