© 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. 120623
    Prev
    Next
    INDEX
    Explanations

    English words followed by 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
    つける
    -0.06
    placement
    -0.06
    ee
    -0.06
    Text
    -0.06
    advertising
    -0.05
     advertising
    -0.05
    አ
    -0.05
     위한
    -0.05
    iar
    -0.05
     luch
    -0.05
    POSITIVE LOGITS
     minimalist
    0.08
     niedr
    0.07
     veldig
    0.07
     zaradi
    0.06
     quod
    0.06
     interoper
    0.06
     overall
    0.06
     компакт
    0.06
     sehr
    0.06
     पारित
    0.06
    Activations Density 0.001%

    No Known Activations