© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130735
    Prev
    Next
    INDEX
    Explanations

    Interface Builder storyboard

    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
     természet
    -0.07
     naturel
    -0.06
    之間的
    -0.06
    poetry
    -0.06
    以及
    -0.06
     beiden
    -0.06
     两
    -0.06
     ព
    -0.06
     curricular
    -0.06
     naturels
    -0.06
    POSITIVE LOGITS
     for
    0.06
     create
    0.06
     代
    0.06
     നില
    0.06
     implic
    0.06
     with
    0.06
     will
    0.06
     spoon
    0.06
    orbit
    0.06
     all
    0.06
    Activations Density 0.002%

    No Known Activations