© 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. 118960
    Prev
    Next
    INDEX
    Explanations

    son of

    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
     HOWEVER
    -0.06
    他
    -0.06
    物が
    -0.06
     queim
    -0.06
     fraudsters
    -0.05
     संभावित
    -0.05
     occasionally
    -0.05
    Ay
    -0.05
    させ
    -0.05
    让他
    -0.05
    POSITIVE LOGITS
     sería
    0.07
     tare
    0.07
    ajuan
    0.07
    城
    0.06
     serían
    0.06
     Bürgermeister
    0.06
     para
    0.06
     Каждый
    0.06
     requiere
    0.06
     crece
    0.06
    Activations Density 0.001%

    No Known Activations