© 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. 117626
    Prev
    Next
    INDEX
    Explanations

    citations and analytical terms

    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
     với
    -0.08
     tatsächlich
    -0.07
     một
    -0.07
     cette
    -0.07
     avec
    -0.06
     có
    -0.06
     と
    -0.06
     هزار
    -0.06
    濠
    -0.06
     sẽ
    -0.06
    POSITIVE LOGITS
     FORM
    0.06
     moreover
    0.05
    ᆭ
    0.05
    办法
    0.05
     droits
    0.05
    🛒
    0.05
    ndash
    0.05
    他
    0.05
     እንዲሁም
    0.05
    ेंबर
    0.05
    Activations Density 0.140%

    No Known Activations