© 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. 119068
    Prev
    Next
    INDEX
    Explanations

    introduction or section headers

    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
     corresponded
    -0.07
     accordingly
    -0.06
     compared
    -0.06
     спро
    -0.06
    Дру
    -0.06
     आइक
    -0.06
    இரு
    -0.06
    読んで
    -0.06
     OFFICIAL
    -0.06
     сравнению
    -0.06
    POSITIVE LOGITS
     nawet
    0.06
     பாதுகா
    0.06
    可以
    0.06
     verwenden
    0.06
     herhangi
    0.06
     optimise
    0.06
     koristiti
    0.05
     लूट
    0.05
     provient
    0.05
    ிற்க
    0.05
    Activations Density 0.001%

    No Known Activations