© 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. 119043
    Prev
    Next
    INDEX
    Explanations

    factor analysis domains

    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
    कांत
    -0.07
     Ka
    -0.06
     পেরে
    -0.06
     changes
    -0.06
    Ka
    -0.06
    之人
    -0.06
    streets
    -0.06
    dirty
    -0.06
    ያስ
    -0.06
     첨
    -0.06
    POSITIVE LOGITS
     দুইটি
    0.06
    均
    0.06
     evenly
    0.06
    ❌
    0.06
    টিআই
    0.06
    лександ
    0.06
     funcionalidad
    0.06
     nekaj
    0.06
    講座
    0.06
     około
    0.06
    Activations Density 0.007%

    No Known Activations