© 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. 130294
    Prev
    Next
    INDEX
    Explanations

    citation brackets

    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
    :
    -0.07
     but
    -0.06
     quatro
    -0.06
     quatre
    -0.06
     do
    -0.06
    四个
    -0.06
     cuatro
    -0.06
    ?
    -0.05
    但在
    -0.05
     execut
    -0.05
    POSITIVE LOGITS
    Additionally
    0.07
     يجعل
    0.07
    While
    0.07
    Không
    0.07
     しかし
    0.07
     While
    0.06
     količ
    0.06
     Despite
    0.06
     contains
    0.06
    Además
    0.06
    Activations Density 0.004%

    No Known Activations