© 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. 130546
    Prev
    Next
    INDEX
    Explanations

    various access multiple additional

    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
     literalmente
    -0.06
     mondo
    -0.06
     bows
    -0.06
     quas
    -0.06
    ቃል
    -0.06
     precluded
    -0.06
     will
    -0.06
     lakes
    -0.06
     soz
    -0.06
     ડિઝ
    -0.06
    POSITIVE LOGITS
    他にも
    0.06
     додат
    0.06
     ilość
    0.06
     jednotliv
    0.06
     மற
    0.06
     zusätzlich
    0.06
    時点で
    0.06
    ze
    0.06
    additional
    0.06
     مسائل
    0.06
    Activations Density 0.012%

    No Known Activations