© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119113
    Prev
    Next
    INDEX
    Explanations

    SQL `ADD_MONTHS`

    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
     многих
    -0.07
     serão
    -0.07
     многие
    -0.07
     many
    -0.07
     вполне
    -0.06
     muitos
    -0.06
     veľ
    -0.06
     combines
    -0.06
     wiele
    -0.06
    Many
    -0.06
    POSITIVE LOGITS
     in
    0.07
     Şu
    0.06
    ultimate
    0.06
     but
    0.06
     attualmente
    0.06
    soy
    0.06
     Quiero
    0.06
    LANG
    0.06
    LOGO
    0.06
    dfs
    0.05
    Activations Density 0.007%

    No Known Activations