© 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. 128690
    Prev
    Next
    INDEX
    Explanations

    collection of items

    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
     বিনিয়োগ
    -0.06
    经历
    -0.06
    經歷
    -0.06
    ,
    -0.06
     કામ
    -0.05
     ア
    -0.05
    TAK
    -0.05
    1
    -0.05
    お
    -0.05
    我已经
    -0.05
    POSITIVE LOGITS
     all
    0.08
    щает
    0.07
     список
    0.07
     مجموعة
    0.07
     కూడా
    0.07
     poate
    0.07
    防水
    0.07
     veramente
    0.07
     всех
    0.07
     também
    0.07
    Activations Density 0.024%

    No Known Activations