© 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. 119035
    Prev
    Next
    INDEX
    Explanations

    constructor

    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
     (
    -0.07
     "
    -0.06
     tovább
    -0.06
    પર
    -0.06
     不
    -0.06
     上
    -0.06
     aún
    -0.06
     在
    -0.06
     这个
    -0.06
     कौन
    -0.05
    POSITIVE LOGITS
     gemeinsame
    0.07
     ony
    0.07
     other
    0.07
     avaient
    0.07
     altri
    0.07
    ؛
    0.07
    meden
    0.07
     unparalleled
    0.07
     andere
    0.07
     seis
    0.07
    Activations Density 0.007%

    No Known Activations