© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 116664
    Prev
    Next
    INDEX
    Explanations

    SP version or edition

    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
     dlatego
    -0.06
     वार्ड
    -0.06
     τελευτα
    -0.06
     سرح
    -0.06
     tidigare
    -0.06
    빼
    -0.06
     바뀌
    -0.06
    することも
    -0.06
     Optimal
    -0.06
    τσι
    -0.06
    POSITIVE LOGITS
     पार्टनर
    0.07
    有哪些
    0.07
    があり
    0.06
    ன்மை
    0.06
    strange
    0.06
     pictures
    0.06
     sensation
    0.06
     proof
    0.06
     Seiten
    0.06
     sekä
    0.06
    Activations Density 0.002%

    No Known Activations