© 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. 118513
    Prev
    Next
    INDEX
    Explanations

    programming method prefixes

    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
     باید
    -0.07
     pitiful
    -0.07
     preferable
    -0.07
     بسبب
    -0.06
    ᔨ
    -0.06
    ประเภท
    -0.06
     itd
    -0.06
     Pirelli
    -0.06
     darf
    -0.06
     entering
    -0.06
    POSITIVE LOGITS
    4
    0.06
     बारीक
    0.06
     Tämä
    0.06
     viszont
    0.06
    1
    0.06
    不
    0.06
    仅仅
    0.05
    மாறு
    0.05
     বাজারের
    0.05
     উৎপাদন
    0.05
    Activations Density 0.001%

    No Known Activations