© 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. 129337
    Prev
    Next
    INDEX
    Explanations

    word after `Genre`, `Does`, `The`, `New`

    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
    解决方法
    -0.07
    зит
    -0.06
     दिखाई
    -0.06
    ruptcy
    -0.06
     gezeigt
    -0.06
    ramique
    -0.06
     cie
    -0.06
    opuerto
    -0.06
     angezeigt
    -0.06
     doigt
    -0.06
    POSITIVE LOGITS
    から
    0.06
     Änderungen
    0.06
     farming
    0.05
     નક્કી
    0.05
    3
    0.05
    0
    0.05
     integr
    0.05
     butternut
    0.05
    िश्च
    0.05
     revising
    0.05
    Activations Density 0.005%

    No Known Activations