© 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. 128615
    Prev
    Next
    INDEX
    Explanations

    number 2

    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
    どんな
    -0.06
     cocinar
    -0.06
    ాలే
    -0.06
    ですね
    -0.06
    ജ
    -0.06
    acceptable
    -0.06
     otrzyma
    -0.06
     धात
    -0.06
     оконча
    -0.05
    POSITIVE LOGITS
     midst
    0.06
     plusieurs
    0.06
     objective
    0.06
     of
    0.06
     viktig
    0.06
    ությունը
    0.06
     метою
    0.06
    อีก
    0.06
    otti
    0.06
     maraming
    0.06
    Activations Density 0.008%

    No Known Activations