© 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. 118920
    Prev
    Next
    INDEX
    Explanations

    sphere, cube, box

    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
     장면
    -0.07
     scenes
    -0.07
     மருத்து
    -0.06
     parts
    -0.06
     непосред
    -0.06
     שני
    -0.06
    ipart
    -0.06
     parte
    -0.06
     główn
    -0.06
    parts
    -0.06
    POSITIVE LOGITS
     निखिल
    0.06
    如果你
    0.06
    ptitle
    0.06
     oxid
    0.06
     اگر
    0.06
    产生的
    0.06
     हूँ
    0.06
     বণ্ট
    0.05
    आय
    0.05
    avour
    0.05
    Activations Density 0.002%

    No Known Activations