© 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. 119283
    Prev
    Next
    INDEX
    Explanations

    package specifications

    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
     перед
    -0.07
     가장
    -0.06
     cautions
    -0.06
     각각
    -0.06
    最为
    -0.06
     सबसे
    -0.06
     लैंड
    -0.06
     এতটা
    -0.06
     zum
    -0.06
     ],
    -0.06
    POSITIVE LOGITS
     NSW
    0.06
    \,\
    0.06
     później
    0.06
     máquinas
    0.06
     și
    0.06
     и
    0.06
     denken
    0.06
    amblea
    0.06
     Wikidata
    0.06
     permanent
    0.06
    Activations Density 0.001%

    No Known Activations