© 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. 128797
    Prev
    Next
    INDEX
    Explanations

    false, None

    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
     in
    -0.07
     प्रमुख
    -0.06
     acerc
    -0.05
     tasty
    -0.05
    huri
    -0.05
    रेक्ट
    -0.05
     香
    -0.05
     XXX
    -0.05
     שלה
    -0.05
     मेट
    -0.05
    POSITIVE LOGITS
    怀疑
    0.07
    我們可以
    0.06
     sceptical
    0.06
    躓
    0.06
     arbitrarily
    0.06
    におすすめ
    0.06
     بشأن
    0.06
     каждому
    0.06
    ຢ
    0.06
     podemos
    0.06
    Activations Density 0.003%

    No Known Activations