© 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. 129024
    Prev
    Next
    INDEX
    Explanations

    Michelle Weber

    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
     véritables
    -0.07
     proven
    -0.06
    puter
    -0.06
     verdadero
    -0.06
     immense
    -0.06
    あの
    -0.05
    CUIT
    -0.05
     karşı
    -0.05
     chosen
    -0.05
     тот
    -0.05
    POSITIVE LOGITS
     jetzt
    0.07
     Jetzt
    0.07
     nyní
    0.07
     now
    0.07
     දැන්
    0.07
     現在
    0.06
     akses
    0.06
    now
    0.06
     இப்போது
    0.06
    现在
    0.06
    Activations Density 0.001%

    No Known Activations