© 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. 116709
    Prev
    Next
    INDEX
    Explanations

    array data access

    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
     zwei
    -0.07
     tidak
    -0.07
     ন্যূনতম
    -0.06
    sized
    -0.06
     although
    -0.06
     acknowledging
    -0.06
     අපි
    -0.06
    サイズの
    -0.06
     autod
    -0.06
     two
    -0.06
    POSITIVE LOGITS
     jeweiligen
    0.06
    izzate
    0.06
     লন্ড
    0.06
     diny
    0.06
     Wex
    0.05
    ire
    0.05
    进入
    0.05
    θεί
    0.05
    cida
    0.05
    ethy
    0.05
    Activations Density 0.001%

    No Known Activations