© 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. 129344
    Prev
    Next
    INDEX
    Explanations

    listing nouns and adjectives

    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
    ørte
    -0.06
    你需要
    -0.06
     Want
    -0.06
     noter
    -0.06
    យ៉
    -0.06
     обычно
    -0.06
    лук
    -0.06
     bezpeč
    -0.06
     产品
    -0.06
    其中包括
    -0.06
    POSITIVE LOGITS
     होऊन
    0.07
     şə
    0.07
    というのは
    0.07
     것처럼
    0.06
     представ
    0.06
     get
    0.06
    เพียง
    0.06
     create
    0.06
    :
    0.06
     refers
    0.06
    Activations Density 0.026%

    No Known Activations