© 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. 129513
    Prev
    Next
    INDEX
    Explanations

    first element

    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
     one
    -0.07
    iviato
    -0.07
     entraî
    -0.07
     один
    -0.07
     یکی
    -0.07
     واحدة
    -0.07
    eleng
    -0.07
    🏚
    -0.06
     unul
    -0.06
     обуча
    -0.06
    POSITIVE LOGITS
     first
    0.07
    (-
    0.06
    first
    0.06
     truncation
    0.06
    First
    0.06
    platform
    0.06
     what
    0.06
     locations
    0.06
    ISupport
    0.06
     የመጀመሪያ
    0.06
    Activations Density 0.001%

    No Known Activations