© 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. 117009
    Prev
    Next
    INDEX
    Explanations

    image generation

    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
     adicionales
    -0.06
    雖
    -0.06
    側の
    -0.06
     absolut
    -0.06
     इनका
    -0.06
    িনিয়র
    -0.06
     ready
    -0.06
    urther
    -0.06
    してます
    -0.06
    OBER
    -0.06
    POSITIVE LOGITS
     when
    0.08
    When
    0.07
    when
    0.07
     我
    0.07
     lorsqu
    0.06
     फार्म
    0.06
     because
    0.06
     عندما
    0.06
     writing
    0.06
    เมื่อ
    0.06
    Activations Density 0.001%

    No Known Activations