© 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. 120175
    Prev
    Next
    INDEX
    Explanations

    solve for variable

    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
    ior
    -0.07
    Vì
    -0.06
    の方は
    -0.06
     being
    -0.06
    håll
    -0.06
    沺
    -0.06
    因为
    -0.06
     শুক্র
    -0.06
    ძ
    -0.06
     possible
    -0.06
    POSITIVE LOGITS
    many
    0.07
    мерикан
    0.06
     czyli
    0.06
     yaitu
    0.06
    before
    0.06
    structed
    0.06
    สัก
    0.06
     Voices
    0.06
     Setelah
    0.06
    द्
    0.06
    Activations Density 0.001%

    No Known Activations