© 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. 116700
    Prev
    Next
    INDEX
    Explanations

    rapper, debut albums

    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
    国际
    -0.07
     dacă
    -0.06
    國際
    -0.06
     pédagog
    -0.06
     internationally
    -0.06
     세계
    -0.06
     ಧ
    -0.06
     animated
    -0.06
    世界の
    -0.06
     olursa
    -0.06
    POSITIVE LOGITS
     زیادی
    0.06
     adequately
    0.06
     नवंबर
    0.06
     cancer
    0.06
     ноябре
    0.06
     durability
    0.06
    石油
    0.06
     briefly
    0.06
     include
    0.06
     ওষুধের
    0.06
    Activations Density 0.007%

    No Known Activations