© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116270
    Prev
    Next
    INDEX
    Explanations

    Neurocutaneous melanosis, quantum theory, @property, @covers

    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
     sicherlich
    -0.07
     segera
    -0.06
     was
    -0.06
     tylko
    -0.06
     also
    -0.06
     فقط
    -0.06
     중요
    -0.06
     certamente
    -0.06
    すぐに
    -0.06
     පෙ
    -0.06
    POSITIVE LOGITS
     GENERAL
    0.06
     sinister
    0.06
     वाटते
    0.06
     General
    0.06
     ট্যাংক
    0.06
     அவற்றில்
    0.06
     Mica
    0.06
    лог
    0.06
    信する
    0.06
     ابنائي
    0.05
    Activations Density 0.002%

    No Known Activations