© 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. 120395
    Prev
    Next
    INDEX
    Explanations

    any, some, or indefinite quantifiers

    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
     by
    -0.08
    🤜
    -0.07
     lengua
    -0.07
     altri
    -0.06
    🐄
    -0.06
     IMHO
    -0.06
     otros
    -0.06
     with
    -0.06
     prawdopod
    -0.06
    POSITIVE LOGITS
     কোনও
    0.07
     কতকগুলি
    0.07
    任何
    0.07
     하나의
    0.07
     एखा
    0.06
     يك
    0.06
     कुनै
    0.06
    떤
    0.06
     ஓர்
    0.06
     आवश्यकता
    0.06
    Activations Density 0.002%

    No Known Activations