© 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. 117650
    Prev
    Next
    INDEX
    Explanations

    Quotes and attributions

    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
     சுமார்
    -0.08
     обычно
    -0.08
    就會
    -0.07
     normalerweise
    -0.07
    Normally
    -0.07
    することにより
    -0.07
     normally
    -0.07
     highly
    -0.07
     routinely
    -0.07
     Normally
    -0.07
    POSITIVE LOGITS
     disini
    0.07
     quei
    0.06
     diberikan
    0.06
     ใน
    0.06
     我
    0.06
     autres
    0.06
     vreau
    0.06
     beinhaltet
    0.06
     t
    0.06
    我对
    0.06
    Activations Density 0.003%

    No Known Activations