© 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. 118258
    Prev
    Next
    INDEX
    Explanations

    in

    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
     Covent
    -0.06
     cik
    -0.06
     собственно
    -0.06
     sev
    -0.05
     অবস্থানে
    -0.05
    ized
    -0.05
     উচ্চ
    -0.05
     request
    -0.05
     cycles
    -0.05
    アクセス
    -0.05
    POSITIVE LOGITS
     ರೀತಿಯ
    0.07
     your
    0.06
     Unfortunately
    0.06
    your
    0.06
     विश्वविद्यालय
    0.06
     Quaker
    0.06
     FAQ
    0.06
     исследователь
    0.06
     ईसाई
    0.06
     illusions
    0.06
    Activations Density 0.007%

    No Known Activations