© 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. 130611
    Prev
    Next
    INDEX
    Explanations

    "${ variable name }"` or `#{ variable }`

    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
    light
    -0.06
    蚵
    -0.06
    hors
    -0.06
    ૉ
    -0.06
     with
    -0.06
    xanth
    -0.05
    给了
    -0.05
    ll
    -0.05
    защи
    -0.05
    with
    -0.05
    POSITIVE LOGITS
     manually
    0.07
     независимо
    0.06
     కోసం
    0.06
     
    0.06
    全面
    0.06
     Gewerks
    0.06
    Global
    0.06
     faktisk
    0.06
    Profit
    0.06
     choosing
    0.06
    Activations Density 0.001%

    No Known Activations