© 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. 119735
    Prev
    Next
    INDEX
    Explanations

    locations near points of interest

    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
     boleh
    -0.06
    frying
    -0.06
     possono
    -0.06
    Sense
    -0.06
     پرویز
    -0.06
     compressor
    -0.06
    ajero
    -0.06
     peuvent
    -0.06
     može
    -0.06
     vít
    -0.06
    POSITIVE LOGITS
     a
    0.09
     an
    0.09
     some
    0.06
     важное
    0.06
     important
    0.06
     కీలక
    0.06
     ethnicity
    0.06
     cinci
    0.06
     importante
    0.06
     impacted
    0.06
    Activations Density 0.004%

    No Known Activations