© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130240
    Prev
    Next
    INDEX
    Explanations

    a serious (relationship)

    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
     ভিত্তিক
    -0.07
     horse
    -0.07
     marshall
    -0.06
     sometimes
    -0.06
     stroke
    -0.06
     cũng
    -0.05
    sometimes
    -0.05
    馳
    -0.05
     часто
    -0.05
     often
    -0.05
    POSITIVE LOGITS
     ਦਿੱ
    0.08
     soient
    0.06
     wyłącznie
    0.06
    ramed
    0.06
     possibilités
    0.06
    按照
    0.06
     महाराष्ट्रा
    0.06
     ánh
    0.06
     Outside
    0.06
    entas
    0.06
    Activations Density 0.001%

    No Known Activations