© 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. 116430
    Prev
    Next
    INDEX
    Explanations

    p53 polymorphisms, different languages

    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
     when
    -0.06
    When
    -0.06
     Feel
    -0.06
     BEFORE
    -0.06
     their
    -0.06
     This
    -0.06
     that
    -0.06
    เมื่อ
    -0.06
     timeless
    -0.06
    This
    -0.06
    POSITIVE LOGITS
    不同
    0.08
     überhaupt
    0.07
     不同
    0.07
     različ
    0.07
    难以
    0.07
    当时
    0.06
     berbeda
    0.06
     вообще
    0.06
     différente
    0.06
     farklı
    0.06
    Activations Density 0.008%

    No Known Activations