© 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. 116871
    Prev
    Next
    INDEX
    Explanations

    XML tags and versioning

    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
    =[
    -0.06
     your
    -0.06
    шчы
    -0.06
     últimos
    -0.06
     _,
    -0.06
    可以选择
    -0.06
     选择
    -0.06
     последних
    -0.06
     yeri
    -0.06
    Choose
    -0.05
    POSITIVE LOGITS
     simplistic
    0.07
     continually
    0.06
     verifiable
    0.06
     Harare
    0.06
    といえば
    0.06
    再度
    0.06
     Collecting
    0.06
     deliciously
    0.06
     perpetually
    0.06
     extraordinarily
    0.06
    Activations Density 0.001%

    No Known Activations