© 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. 119652
    Prev
    Next
    INDEX
    Explanations

    programming keywords and constructs

    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
     Vogel
    -0.06
     sanitation
    -0.06
     there
    -0.06
    there
    -0.06
    Providing
    -0.06
     WOMEN
    -0.06
     Anzahl
    -0.06
     Verte
    -0.06
     contribu
    -0.06
    agge
    -0.06
    POSITIVE LOGITS
     होमवर्क
    0.06
     attic
    0.06
    കര്‍
    0.06
    众多
    0.06
     이후
    0.06
     également
    0.05
     internal
    0.05
    hoo
    0.05
     acest
    0.05
     patio
    0.05
    Activations Density 0.001%

    No Known Activations