© 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. 118873
    Prev
    Next
    INDEX
    Explanations

    median followed by a statistic

    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
    Liqu
    -0.06
     that
    -0.06
     greener
    -0.06
    There
    -0.06
     Liqu
    -0.06
     there
    -0.06
    cole
    -0.06
    ank
    -0.05
    غط
    -0.05
    grounds
    -0.05
    POSITIVE LOGITS
     হওয়া
    0.07
     πρέπει
    0.07
     coisa
    0.06
     doit
    0.06
    无法
    0.06
     debe
    0.06
     dificuldade
    0.06
     wśród
    0.06
     mı
    0.06
     должно
    0.06
    Activations Density 0.002%

    No Known Activations