© 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. 116225
    Prev
    Next
    INDEX
    Explanations

    legal case parties

    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
     INITIAL
    -0.08
    INITIAL
    -0.07
    Initial
    -0.06
    loge
    -0.06
     Initial
    -0.06
     Applicable
    -0.06
     initiale
    -0.06
     Initially
    -0.06
     Update
    -0.06
    Inicial
    -0.05
    POSITIVE LOGITS
     وليس
    0.07
    できる
    0.07
     should
    0.07
    ができる
    0.06
     থাকার
    0.06
    Readers
    0.06
     quien
    0.06
    should
    0.06
     now
    0.06
     වා
    0.06
    Activations Density 0.001%

    No Known Activations