© 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. 130348
    Prev
    Next
    INDEX
    Explanations

    operators and punctuation

    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
     to
    -0.08
     ngayon
    -0.06
     at
    -0.06
     læ
    -0.06
     günst
    -0.06
     inzwischen
    -0.06
     volledig
    -0.06
     complètement
    -0.06
     дове
    -0.06
     다섯
    -0.06
    POSITIVE LOGITS
    ;
    0.07
     unsatisf
    0.07
     그리고
    0.06
     તેમજ
    0.06
     unacceptable
    0.06
    |
    0.06
     तथा
    0.06
     اما
    0.06
    그리고
    0.06
     sekä
    0.06
    Activations Density 0.001%

    No Known Activations