© 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. 118658
    Prev
    Next
    INDEX
    Explanations

    "`foo` `1` `height`"

    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
     中的
    -0.07
     중에서
    -0.06
    ➢
    -0.06
     cAMP
    -0.06
     pels
    -0.06
     에서
    -0.06
     によって
    -0.06
     ALEXANDER
    -0.06
     pang
    -0.06
     halted
    -0.06
    POSITIVE LOGITS
     permeable
    0.06
    जन्
    0.06
     پہلے
    0.05
     Neph
    0.05
     झर
    0.05
     बगैर
    0.05
     Permit
    0.05
     प्रेग्न
    0.05
     abduction
    0.05
     [
    0.05
    Activations Density 0.001%

    No Known Activations