© 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. 120562
    Prev
    Next
    INDEX
    Explanations

    code identifiers and separators

    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
     WHAT
    -0.06
    ó
    -0.06
     video
    -0.06
    半
    -0.06
    홍
    -0.06
    อะไร
    -0.06
     loosely
    -0.06
     humid
    -0.06
    יר
    -0.05
     on
    -0.05
    POSITIVE LOGITS
     already
    0.07
     potens
    0.07
     вже
    0.07
    过程中
    0.06
     עס
    0.06
     supposed
    0.06
     بالفعل
    0.06
    already
    0.06
    過程中
    0.06
     sciatica
    0.06
    Activations Density 0.002%

    No Known Activations