© 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. 119387
    Prev
    Next
    INDEX
    Explanations

    disable, block, or manage

    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
     کنس
    -0.06
     implicitly
    -0.06
     সং
    -0.06
     консо
    -0.06
     लॉन्
    -0.06
     uttered
    -0.06
     শুনি
    -0.06
     প্লা
    -0.06
     Raum
    -0.05
    webkit
    -0.05
    POSITIVE LOGITS
     estimados
    0.06
     overcoming
    0.06
     könnten
    0.06
    道德
    0.06
     cloud
    0.06
     reproduction
    0.06
     مقدس
    0.06
     grootste
    0.06
     Reproduction
    0.06
     strictement
    0.06
    Activations Density 0.003%

    No Known Activations