© 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. 119218
    Prev
    Next
    INDEX
    Explanations

    Hubble Space Telescope

    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
     troppo
    -0.07
     costru
    -0.06
     সাবধান
    -0.06
     Klang
    -0.06
     بلغ
    -0.06
     contatto
    -0.06
    build
    -0.06
     постро
    -0.06
     bohemian
    -0.06
    也可
    -0.06
    POSITIVE LOGITS
    ច្
    0.07
     imaged
    0.06
     ED
    0.06
     gorgeous
    0.06
    শর
    0.06
    蝦
    0.06
     enemies
    0.06
     görüntü
    0.06
     eid
    0.06
     gorge
    0.06
    Activations Density 0.002%

    No Known Activations