© 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. 130357
    Prev
    Next
    INDEX
    Explanations

    particle beam therapy, particle radiation

    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
     SMALL
    -0.07
    小型
    -0.06
     combines
    -0.06
     квар
    -0.06
     vivent
    -0.06
    治安
    -0.06
    ignty
    -0.05
    temuan
    -0.05
    tidy
    -0.05
     merger
    -0.05
    POSITIVE LOGITS
     Prasad
    0.06
     ziel
    0.06
     پیچ
    0.06
     tunnels
    0.06
     skrz
    0.06
     žmog
    0.06
     tunnel
    0.06
     wheelchairs
    0.06
    얽
    0.06
     χρόνια
    0.06
    Activations Density 0.011%

    No Known Activations