© 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. 130625
    Prev
    Next
    INDEX
    Explanations

    medical conditions, biological entities, or market 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
     taman
    -0.06
     gelen
    -0.06
     constantemente
    -0.06
    +{\
    -0.06
     약간
    -0.06
     dokładnie
    -0.06
    Collaboration
    -0.06
     समझौ
    -0.06
    seal
    -0.06
    hemer
    -0.06
    POSITIVE LOGITS
     such
    0.06
     എന്നീ
    0.06
    ф
    0.06
     sådan
    0.06
     অস্ত
    0.06
    such
    0.06
    ^^
    0.06
     as
    0.06
     अस्तित्व
    0.05
     दिसून
    0.05
    Activations Density 0.010%

    No Known Activations