© 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. 130704
    Prev
    Next
    INDEX
    Explanations

    question or punctuation followed by text

    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
     will
    -0.08
     obecnie
    -0.07
     θα
    -0.06
     خلال
    -0.06
     actualmente
    -0.06
     jointly
    -0.06
     сучас
    -0.06
    ித்து
    -0.06
     אס
    -0.06
     weekly
    -0.06
    POSITIVE LOGITS
     सोचने
    0.07
     было
    0.07
     estava
    0.06
     estaban
    0.06
     new
    0.06
     praticamente
    0.06
     estavam
    0.06
     favored
    0.06
     newfound
    0.06
     kanyang
    0.06
    Activations Density 0.008%

    No Known Activations