© 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. 116673
    Prev
    Next
    INDEX
    Explanations

    since then

    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
     this
    -0.07
     এই
    -0.07
    ፂ
    -0.07
     denoting
    -0.07
     these
    -0.07
     añade
    -0.06
     commemorating
    -0.06
     now
    -0.06
     providing
    -0.06
    Sensor
    -0.06
    POSITIVE LOGITS
    就能
    0.06
     পরিশ
    0.06
     \|
    0.06
    従業
    0.06
    满了
    0.06
     could
    0.06
     re
    0.05
    丝
    0.05
     actively
    0.05
     revamp
    0.05
    Activations Density 0.008%

    No Known Activations