© 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. 118968
    Prev
    Next
    INDEX
    Explanations

    !!! ..... >>> ,, mmm yy

    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
     for
    -0.06
    使用
    -0.06
     bulunan
    -0.06
    採用
    -0.06
     request
    -0.06
     ansatz
    -0.06
     teorema
    -0.05
     до
    -0.05
    ginx
    -0.05
    픈
    -0.05
    POSITIVE LOGITS
     !!!!!
    0.07
    !!!!!
    0.07
     !!
    0.07
    .........
    0.07
     .........
    0.06
    ............
    0.06
    .....
    0.06
    ........
    0.06
    .............
    0.06
    把握
    0.06
    Activations Density 0.016%

    No Known Activations