© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131021
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    Sampling
    -0.07
    Sample
    -0.06
     sampling
    -0.06
    আমার
    -0.06
    kowych
    -0.05
    textrm
    -0.05
     Sampling
    -0.05
     billion
    -0.05
    prisingly
    -0.05
    Mostly
    -0.05
    POSITIVE LOGITS
     ولكن
    0.06
     Regierung
    0.06
    まぁ
    0.06
     görür
    0.06
     щоб
    0.06
     어린이
    0.06
    ቻል
    0.06
     بحيث
    0.06
    雖然
    0.06
     alleen
    0.06
    Activations Density 0.010%

    No Known Activations