© 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. 119072
    Prev
    Next
    INDEX
    Explanations

    variants, norms, origin, must

    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
     adress
    -0.06
    떄
    -0.06
     moze
    -0.06
     succes
    -0.06
     the
    -0.06
     وبا
    -0.06
     imposible
    -0.06
     apropri
    -0.05
     ամ
    -0.05
     initiale
    -0.05
    POSITIVE LOGITS
    ,
    0.08
    ၊
    0.07
    Also
    0.06
     Также
    0.06
     contrairement
    0.06
    ágot
    0.06
     također
    0.06
     vlá
    0.06
     также
    0.06
     Therefore
    0.06
    Activations Density 0.046%

    No Known Activations