© 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. 118475
    Prev
    Next
    INDEX
    Explanations

    TV series and names

    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
     çocuklar
    -0.08
     kinderen
    -0.08
     children
    -0.07
     فرزند
    -0.07
     антен
    -0.07
    孩子们
    -0.07
     Azərbaycan
    -0.06
     grinning
    -0.06
     ಮಕ್ಕಳ
    -0.06
     детьми
    -0.06
    POSITIVE LOGITS
     Recurs
    0.06
    Land
    0.06
     differentiable
    0.06
     descre
    0.05
    ತಿಯ
    0.05
    anci
    0.05
    ્રી
    0.05
     patient
    0.05
    患者
    0.05
    Recurs
    0.05
    Activations Density 0.001%

    No Known Activations