© 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. 129011
    Prev
    Next
    INDEX
    Explanations

    website code structures

    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
     Half
    -0.07
    전을
    -0.06
    autor
    -0.06
     반려동
    -0.06
     হত
    -0.06
    setMaximum
    -0.06
     excessive
    -0.06
     recommended
    -0.06
    著作
    -0.06
     exs
    -0.06
    POSITIVE LOGITS
     can
    0.06
    BITMAP
    0.06
     kleuren
    0.06
     ordre
    0.06
     ámbitos
    0.06
     chantier
    0.05
     couleur
    0.05
     सीमेंट
    0.05
     знаете
    0.05
     does
    0.05
    Activations Density 0.006%

    No Known Activations