© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129475
    Prev
    Next
    INDEX
    Explanations

    periods and then subsequent phrases

    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
     প্রক্র
    -0.06
     relocating
    -0.06
     Decrease
    -0.06
     poiché
    -0.06
     dimensionality
    -0.06
     converging
    -0.06
     മാ
    -0.06
     perny
    -0.06
     positif
    -0.06
     bogus
    -0.06
    POSITIVE LOGITS
    虽
    0.06
    虽然
    0.06
     evitar
    0.06
     इंस्टाग्राम
    0.06
     توصیه
    0.05
    ид
    0.05
     虽然
    0.05
    ミニ
    0.05
     Embora
    0.05
     still
    0.05
    Activations Density 0.001%

    No Known Activations