© 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. 129503
    Prev
    Next
    INDEX
    Explanations

    code delimiters and numbers

    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
    full
    -0.07
    ুখী
    -0.05
    elabor
    -0.05
     Read
    -0.05
     ensue
    -0.05
     navigate
    -0.05
    FULL
    -0.05
    Won
    -0.05
    Source
    -0.05
     വിവിധ
    -0.05
    POSITIVE LOGITS
     thereby
    0.07
     zaidi
    0.07
     regions
    0.07
     ursprünglich
    0.07
     zudem
    0.06
     debido
    0.06
     кален
    0.06
     dadurch
    0.06
     inoltre
    0.06
    డంతో
    0.06
    Activations Density 0.001%

    No Known Activations