© 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. 116397
    Prev
    Next
    INDEX
    Explanations

    maven pom.xml plugin declarations

    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
     ស
    -0.07
     کودکان
    -0.06
     отличается
    -0.06
     profiles
    -0.06
     uygulam
    -0.06
     employs
    -0.06
     is
    -0.06
     involves
    -0.06
     caracter
    -0.06
     combines
    -0.06
    POSITIVE LOGITS
     being
    0.06
    必须要
    0.06
    不要
    0.06
    then
    0.06
     flound
    0.06
     intolerable
    0.06
     Verme
    0.06
     Logic
    0.06
     مثلا
    0.06
     mostly
    0.06
    Activations Density 0.001%

    No Known Activations