© 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. 118420
    Prev
    Next
    INDEX
    Explanations

    future

    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
     oude
    -0.08
     put
    -0.06
     njihov
    -0.06
     chose
    -0.06
    晚上
    -0.06
     plagued
    -0.06
     ночью
    -0.06
     oble
    -0.06
    鯉
    -0.06
    ⌞
    -0.06
    POSITIVE LOGITS
    Fi
    0.06
     }}
    0.06
    łuż
    0.06
    avoir
    0.06
     MB
    0.06
    一般
    0.05
    Brig
    0.05
     এই
    0.05
    Less
    0.05
    crets
    0.05
    Activations Density 0.010%

    No Known Activations