© 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. 118030
    Prev
    Next
    INDEX
    Explanations

    here is

    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
     громад
    -0.06
     Determination
    -0.06
    ؤ
    -0.06
    bur
    -0.06
    zoek
    -0.05
    LETIN
    -0.05
    Viol
    -0.05
     prijatel
    -0.05
     besser
    -0.05
     потен
    -0.05
    POSITIVE LOGITS
     aerospace
    0.06
     ਆਪਣੇ
    0.06
     프로그램을
    0.06
     Aerospace
    0.06
    ாளர்
    0.06
    dades
    0.06
    ขอ
    0.06
     dapat
    0.06
    まずは
    0.06
     ระยะ
    0.06
    Activations Density 0.009%

    No Known Activations