© 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. 130463
    Prev
    Next
    INDEX
    Explanations

    dates and events

    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
     മേഖല
    -0.08
     nơi
    -0.07
     sinistra
    -0.07
     fluxo
    -0.07
     helplessly
    -0.06
    '+
    -0.06
     nessuna
    -0.06
     primeros
    -0.06
     prevista
    -0.06
     pierwszej
    -0.06
    POSITIVE LOGITS
     new
    0.06
     inclusions
    0.06
     true
    0.06
    Georgian
    0.06
     Your
    0.06
     आधा
    0.05
    ^^^^
    0.05
     anew
    0.05
    ↵
    0.05
     એલ
    0.05
    Activations Density 0.005%

    No Known Activations