© 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. 119128
    Prev
    Next
    INDEX
    Explanations

    Simon Says

    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
     영향을
    -0.06
    فتح
    -0.06
     собственного
    -0.06
     mound
    -0.06
     одном
    -0.06
     waits
    -0.06
     наличи
    -0.06
    﨑
    -0.06
    रीय
    -0.06
     μόνο
    -0.06
    POSITIVE LOGITS
    AsyncTask
    0.06
    控制
    0.06
     it
    0.06
     ব্যর্থ
    0.06
     tới
    0.06
     fault
    0.06
     अल्ट
    0.06
    BOSS
    0.06
    carbam
    0.06
     devemos
    0.06
    Activations Density 0.020%

    No Known Activations